© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 11858
    Prev
    Next
    INDEX
    Explanations

    rules and safety

    np_max-act · gemini-2.0-flash

    guidance that explicitly emphasizes safety, legality, consent, and appropriateness—often as cautionary qualifiers within advice.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hbox
    -0.08
    CGSize
    -0.07
    _Settings
    -0.07
    otherapy
    -0.07
    raising
    -0.07
    (button
    -0.07
    Justin
    -0.07
    .maven
    -0.07
    _vk
    -0.07
    	flex
    -0.07
    POSITIVE LOGITS
     remainder
    0.07
    culo
    0.07
    ➹
    0.07
     début
    0.07
     after
    0.07
    .addActionListener
    0.07
    不甘
    0.07
    斠
    0.06
    ⇞
    0.06
     IMS
    0.06
    Activations Density 0.146%

    No Known Activations