© 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. 95944
    Prev
    Next
    INDEX
    Explanations

    bump

    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
    ç»ı纪人
    -0.28
    idget
    -0.27
     bankrupt
    -0.27
     Burr
    -0.25
     boring
    -0.25
    æĽ´å¤ļä¿¡æģ¯
    -0.24
     crumbling
    -0.23
    èIJĮ
    -0.23
    çľ¨çľ¼
    -0.23
    [arr
    -0.23
    POSITIVE LOGITS
    åijµ
    0.34
    side
    0.32
    檫
    0.30
    sync
    0.28
    ware
    0.28
    yc
    0.28
    meth
    0.27
    wow
    0.27
     sync
    0.27
    åĺ¿
    0.26
    Activations Density 0.010%

    No Known Activations