© 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. 18395
    Prev
    Next
    INDEX
    Explanations

    Ul

    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
    该åħ¬åı¸
    -0.27
    ephy
    -0.25
    èĮ¨
    -0.25
    rss
    -0.24
    compound
    -0.24
     Soldier
    -0.23
     Shock
    -0.23
    Av
    -0.23
     Chips
    -0.23
    olec
    -0.23
    POSITIVE LOGITS
    stile
    0.28
    ç©·
    0.28
    ure
    0.27
    æĺĤ
    0.25
    kaar
    0.24
    åľ¨æĦı
    0.24
    /sql
    0.24
    /pub
    0.24
     hur
    0.24
    ylim
    0.24
    Activations Density 0.029%

    No Known Activations