© 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. 129519
    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
    acf
    -0.27
    newInstance
    -0.27
    obao
    -0.26
    oms
    -0.25
     Series
    -0.25
     series
    -0.24
     Brothers
    -0.24
    派人
    -0.24
    TX
    -0.24
    unta
    -0.24
    POSITIVE LOGITS
    ivial
    0.26
    æ´»ä¸ĭåİ»
    0.26
    ipes
    0.26
    åįłåľ°éĿ¢ç§¯
    0.25
    æĬĺ
    0.25
    éĺµ
    0.24
    elry
    0.24
    aley
    0.24
    æĦıä¹ī
    0.23
    áºŃn
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.