© 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. 35-TRANSCODER-HP
    7. 39415
    Prev
    Next
    INDEX
    Explanations

    Parenthesis/quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    one
    -0.31
    ones
    -0.30
    est
    -0.30
    used
    -0.28
    ex
    -0.28
    æľīæ¯Ĵ
    -0.28
    ens
    -0.28
    le
    -0.27
    ½
    -0.27
    equals
    -0.26
    POSITIVE LOGITS
    ting
    0.32
    gne
    0.30
    odom
    0.28
    rzy
    0.28
     ÐŀÐŀ
    0.28
     Gale
    0.27
     CCP
    0.26
     Horde
    0.26
    ton
    0.26
    .bc
    0.25
    Activations Density 70.628%

    No Known Activations