© 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. 96688
    Prev
    Next
    INDEX
    Explanations

    law

    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
     walker
    -0.27
    amide
    -0.27
    ausible
    -0.26
    bens
    -0.26
    andel
    -0.26
     hold
    -0.25
     createElement
    -0.25
    na
    -0.25
     açıl
    -0.25
     trial
    -0.24
    POSITIVE LOGITS
    é¡¿
    0.29
    .Dir
    0.29
    éłĵ
    0.27
    éĿ¢å¯¹
    0.27
    èĮĥ
    0.27
    eros
    0.27
    è§Ħ
    0.26
    èĥĮåIJİ
    0.25
    .nih
    0.25
     Lib
    0.25
    Activations Density 0.106%

    No Known Activations