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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 44207
    Prev
    Next
    INDEX
    Explanations

    overall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    全身
    -0.07
     lump
    -0.07
    Answer
    -0.07
    늙
    -0.06
    するのが
    -0.06
    (section
    -0.06
    SECTION
    -0.06
     displayed
    -0.06
    催生
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    五年
    0.07
    高空
    0.07
    _evaluation
    0.07
     (){↵
    0.07
    .None
    0.06
    each
    0.06
    闲
    0.06
    开盘
    0.06
    铑
    0.06
     Lesbian
    0.06
    Activations Density 0.003%

    No Known Activations