© 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. 95413
    Prev
    Next
    INDEX
    Explanations

    leaf/leaves

    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
     Agency
    -0.30
     agency
    -0.29
     agencies
    -0.28
    aho
    -0.26
    çļĦæ¶Īæģ¯
    -0.26
    Naz
    -0.26
    æ¶Īæģ¯
    -0.26
     MES
    -0.25
     Agencies
    -0.25
    vor
    -0.25
    POSITIVE LOGITS
    åĴĮ个人
    0.31
    iture
    0.29
    eline
    0.28
    itarian
    0.28
    irting
    0.26
    grams
    0.26
    é«ĺä½İ
    0.26
    binations
    0.26
    .LayoutParams
    0.25
     weekends
    0.25
    Activations Density 0.004%

    No Known Activations