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. 23-RESID-POST-AA
    6. 118
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gon
    -0.07
    -bin
    -0.07
    .Sc
    -0.07
     determining
    -0.07
    法官
    -0.07
    ining
    -0.07
    ﱐ
    -0.07
    掌握了
    -0.07
    大师
    -0.06
    ਮ
    -0.06
    POSITIVE LOGITS
    ኖ
    0.07
     сдел
    0.07
     conhec
    0.07
    sparse
    0.07
    )[-
    0.07
    OP
    0.07
     OrderedDict
    0.07
    工作任务
    0.07
    _UNDEFINED
    0.07
    protocol
    0.07
    Activations Density 0.024%

    No Known Activations