© 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. 96167
    Prev
    Next
    INDEX
    Explanations

    computer, software

    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
     Algeria
    -0.28
     ÑģÑĤал
    -0.28
    Meet
    -0.26
    _mx
    -0.26
     sdk
    -0.26
    æİ¥åĪ°
    -0.26
    æ°¨éħ¸
    -0.25
    _sdk
    -0.25
    åĮħåĮħ
    -0.25
    ç³»ç»Ł
    -0.25
    POSITIVE LOGITS
    åŁŁ
    0.32
     Sup
    0.31
     center
    0.30
     SUP
    0.30
    ä¸Ńå¿ĥ
    0.29
     contrast
    0.29
    center
    0.29
     Contrast
    0.29
     Center
    0.28
    Center
    0.28
    Activations Density 0.974%

    No Known Activations