© 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. 87491
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æµģæ°´
    -0.28
    åľ¨ä¸Ĭæµ·
    -0.26
    .Intent
    -0.26
    客æĪ·æľįåĬ¡
    -0.24
     within
    -0.24
     c
    -0.23
     winner
    -0.23
    åľ¨åĽ½åĨħ
    -0.23
    羣çĪ±
    -0.23
    æħĪ
    -0.23
    POSITIVE LOGITS
     strr
    0.26
    ä¹İ
    0.25
    anine
    0.25
    _Public
    0.25
    .gnu
    0.24
     поÑģл
    0.24
     REC
    0.24
    _ET
    0.23
    ана
    0.23
    å´ŀ
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.