© 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. 18231
    Prev
    Next
    INDEX
    Explanations

    java code snippets

    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
    lox
    -0.28
    ^K
    -0.27
     UUID
    -0.26
     integral
    -0.26
    \CMS
    -0.25
    cao
    -0.25
    UUID
    -0.24
     Costs
    -0.23
     Whereas
    -0.23
     mud
    -0.23
    POSITIVE LOGITS
    ä¹Ŀ大
    0.30
    -boy
    0.29
    essler
    0.25
    olecule
    0.25
    åŁºæľ¬æĥħåĨµ
    0.25
    pped
    0.25
    bris
    0.24
    artner
    0.24
     MenuItem
    0.24
    PointerType
    0.24
    Activations Density 0.105%

    No Known Activations