© 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. 111499
    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
    è¶Ĭ大
    -0.27
    uces
    -0.25
    gu
    -0.23
    家éķ¿ä»¬
    -0.23
     uncertain
    -0.23
    bum
    -0.22
    éĹ´
    -0.22
    orientation
    -0.22
    essler
    -0.22
     bigger
    -0.22
    POSITIVE LOGITS
    çī½
    0.29
    ich
    0.28
    ailles
    0.26
    èIJĿ
    0.24
    æģ¼
    0.24
    .capture
    0.24
    ovie
    0.24
    chine
    0.23
    âu
    0.23
    memberof
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.