© 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. 22-TRANSCODER-HP
    7. 98110
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iesta
    -0.27
     Actions
    -0.25
    æ½®
    -0.24
    -summary
    -0.24
     ens
    -0.24
    âĸĪâĸĪ
    -0.23
    vida
    -0.23
    æĿ¥åĽŀ
    -0.23
    UIL
    -0.23
    ongoose
    -0.23
    POSITIVE LOGITS
     toured
    0.26
    ä»İæĿ¥
    0.25
     nécess
    0.25
    NewProp
    0.23
     emptied
    0.23
    åľ¨è¿Ļæĸ¹éĿ¢
    0.23
    ght
    0.23
     Apt
    0.23
     competitions
    0.23
     ZEND
    0.22
    Activations Density 0.006%

    No Known Activations