© 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. 88069
    Prev
    Next
    INDEX
    Explanations

    Code/Technical Documentation

    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
    asaki
    -0.26
    符åIJĪ
    -0.26
    åij½
    -0.26
    -years
    -0.25
    Direct
    -0.24
    respect
    -0.24
    [](
    -0.24
     dire
    -0.24
    ,set
    -0.24
    æ¿Ģ
    -0.24
    POSITIVE LOGITS
     intros
    0.28
     hoops
    0.27
     entail
    0.27
    defs
    0.26
    inee
    0.26
    ç¾İ人
    0.26
    opsis
    0.25
    è¡Ĺä¸Ĭ
    0.25
    uma
    0.24
     nearer
    0.24
    Activations Density 0.006%

    No Known Activations