© 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. 98066
    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
    emade
    -0.28
    chy
    -0.27
     Playground
    -0.27
     playground
    -0.26
    åij¢
    -0.26
    ulin
    -0.26
    æīįè¡Į
    -0.26
    åĵ©
    -0.24
     bh
    -0.24
    qv
    -0.23
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.26
    åģıåģı
    0.26
    æ°´åĩĨ
    0.26
    éĢļçĶ¨
    0.25
    è·Ĺ
    0.25
    éĸ£
    0.24
    боÑĢ
    0.24
    é«ĺé¢Ŀ
    0.24
    metic
    0.24
    åѦ龸
    0.24
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.