© 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. 32-TRANSCODER-HP
    7. 42864
    Prev
    Next
    INDEX
    Explanations

    positive change or impact

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rare
    -0.27
    ationale
    -0.27
    ä¸įåľ¨ä¹İ
    -0.25
    åįļ主
    -0.25
    åĪ³
    -0.25
    icult
    -0.24
     excerpts
    -0.23
    AccessException
    -0.23
    èĻı
    -0.23
    ä¸Ń级
    -0.23
    POSITIVE LOGITS
     different
    0.33
     a
    0.32
    ä¸įåIJĮ
    0.32
     real
    0.31
    寸
    0.30
     différent
    0.28
    _ABI
    0.27
    od
    0.27
    æŁ¥
    0.26
     off
    0.25
    Activations Density 0.002%

    No Known Activations