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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108092
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     able
    -0.28
    look
    -0.26
    èĥ½å¤Ł
    -0.26
    éĥ½èĥ½å¤Ł
    -0.25
    acos
    -0.25
    èĥ½å¤Łåľ¨
    -0.25
    åħĪéĶĭ
    -0.25
    .tpl
    -0.24
    èĥ½å¤Łè®©
    -0.24
     pouvoir
    -0.24
    POSITIVE LOGITS
    ultz
    0.27
    crast
    0.27
    åģļ大
    0.26
    ToJson
    0.26
    insky
    0.25
    åѸçĶŁ
    0.24
    engan
    0.24
    .did
    0.24
    [hash
    0.24
    creens
    0.24
    Activations Density 0.921%

    No Known Activations