Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77458
    Prev
    Next
    INDEX
    Explanations

    promotional/expository sentences that introduce an offering and explain its purpose, capabilities, and intended users.

    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
    (urls
    -0.07
    萧
    -0.07
     представлен
    -0.07
    ㆀ
    -0.07
    分别为
    -0.07
     Link
    -0.07
     Legisl
    -0.07
    瀹
    -0.07
    込まれ
    -0.07
     buổi
    -0.07
    POSITIVE LOGITS
     packing
    0.07
    notation
    0.07
    _SELECTION
    0.07
    кий
    0.07
    onClick
    0.07
    .net
    0.07
    _key
    0.07
    _due
    0.07
    CTION
    0.07
    .fix
    0.06
    Activations Density 0.652%

    No Known Activations