© 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. 88136
    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
     Consum
    -0.27
    consum
    -0.25
    ENUM
    -0.24
    好æ¶Īæģ¯
    -0.24
    ocator
    -0.24
    ä¸ĢæŶ
    -0.24
     Rolled
    -0.23
     consum
    -0.23
    Enumer
    -0.23
    æŀļ
    -0.23
    POSITIVE LOGITS
    ç°¿
    0.31
    å§Ķæīĺ
    0.29
     earm
    0.25
    oon
    0.24
    _START
    0.24
    кÑģ
    0.24
    .toBe
    0.23
    å¿Ĵ
    0.23
    Ñģен
    0.23
    THING
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.