© 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. 98363
    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
    ç¾ģ
    -0.30
    cred
    -0.28
     crossover
    -0.26
    æ´²
    -0.26
    dio
    -0.26
    ppy
    -0.25
    æĸľ
    -0.25
    ç¹ģ
    -0.24
    DET
    -0.24
    onet
    -0.24
    POSITIVE LOGITS
     tentative
    0.26
    estone
    0.26
    åĴ¨è¯¢æľįåĬ¡
    0.24
    çļĦåħ´è¶£
    0.24
    mdir
    0.24
    æĢĢçĿĢ
    0.24
    AMAGE
    0.24
    Vectorizer
    0.24
    鸣
    0.23
    è·³
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.