© 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. 95912
    Prev
    Next
    INDEX
    Explanations

    Treaty

    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
     sw
    -0.28
     Hunters
    -0.27
    æľºåĪ¶
    -0.25
    è¿Ľåĩº
    -0.25
     Robbins
    -0.25
    ÐŀÐĿ
    -0.25
    .inspect
    -0.24
    ç¦ģ
    -0.24
    _plural
    -0.23
     Cur
    -0.23
    POSITIVE LOGITS
    arLayout
    0.33
     tack
    0.28
    建çŃijéĿ¢ç§¯
    0.28
     ISSUE
    0.27
     Dane
    0.27
    客æĪ·éľĢæ±Ĥ
    0.27
    æ¼ķ
    0.26
    tlement
    0.25
    RAY
    0.25
    ril
    0.25
    Activations Density 0.884%

    No Known Activations