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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 71393
    Prev
    Next
    INDEX
    Explanations

    Computer/phone activity

    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
     celebrate
    -0.08
    美元
    -0.07
     dismissed
    -0.07
    疰
    -0.07
    [child
    -0.07
    miş
    -0.07
    filename
    -0.07
     newList
    -0.07
    万欧元
    -0.07
     wire
    -0.07
    POSITIVE LOGITS
    _ac
    0.08
    켰
    0.07
     procrast
    0.07
     molest
    0.07
    _party
    0.07
    _MAP
    0.07
     THINK
    0.07
    كوم
    0.07
    accum
    0.07
     Reform
    0.06
    Activations Density 0.208%

    No Known Activations