© 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. 19307
    Prev
    Next
    INDEX
    Explanations

    dB

    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
    -Length
    -0.32
    leased
    -0.29
     Length
    -0.28
    pread
    -0.28
     LENGTH
    -0.27
     ENC
    -0.27
    dbh
    -0.27
    hower
    -0.27
    管çIJĨåĪ¶åº¦
    -0.26
    IBE
    -0.26
    POSITIVE LOGITS
    s
    0.45
    spl
    0.40
    MER
    0.30
     spl
    0.30
    squ
    0.29
    olang
    0.29
    sure
    0.28
    çļĦ带é¢Ĩ
    0.27
    sad
    0.27
     optim
    0.26
    Activations Density 0.094%

    No Known Activations