© 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. 30-TRANSCODER-HP
    7. 96518
    Prev
    Next
    INDEX
    Explanations

    Eat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usan
    -0.28
    away
    -0.26
    loff
    -0.26
    ashi
    -0.25
     Held
    -0.25
    离
    -0.25
    raham
    -0.25
    msgid
    -0.25
    els
    -0.24
    éĢŀ
    -0.24
    POSITIVE LOGITS
     Pent
    0.25
    erce
    0.25
     Ur
    0.24
     Nev
    0.24
    æİ
    0.24
    æ²½
    0.24
    Ok
    0.23
    PU
    0.23
    Subset
    0.23
    .ta
    0.23
    Activations Density 0.883%

    No Known Activations