© 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. 31-TRANSCODER-HP
    7. 18834
    Prev
    Next
    INDEX
    Explanations

    Unstructured data/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TK
    -0.31
    vant
    -0.28
    ickey
    -0.25
    ноÑģÑĤ
    -0.25
     tk
    -0.25
    zu
    -0.25
    ialized
    -0.25
    issan
    -0.25
     Paz
    -0.25
     twe
    -0.24
    POSITIVE LOGITS
    aits
    0.29
    ç»ĻåŃ©åŃIJ
    0.29
     Redistributions
    0.27
    oque
    0.27
    _SYN
    0.27
    (coll
    0.26
    æŃĩ
    0.26
    feeds
    0.26
     synchronize
    0.26
    adena
    0.25
    Activations Density 0.134%

    No Known Activations