© 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. 95451
    Prev
    Next
    INDEX
    Explanations

    research reports

    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
    mast
    -0.28
    ç¥Ŀ
    -0.27
    à¹Ħ
    -0.26
    lesia
    -0.25
     ust
    -0.25
     cost
    -0.25
     Rack
    -0.24
    è¿ĩ大
    -0.24
     commission
    -0.24
     Erect
    -0.24
    POSITIVE LOGITS
    æµ·æ´ĭ
    0.26
    reveal
    0.25
    -General
    0.24
    æŁ¥éªĮ
    0.24
    åĨįä¹Łä¸į
    0.24
    xes
    0.24
    é£İäºij
    0.23
    åĽŃåĮº
    0.23
     Vari
    0.23
     jc
    0.23
    Activations Density 0.095%

    No Known Activations