© 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. 129961
    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
    eto
    -0.28
     leo
    -0.28
    åľ¨ä¸Ĭæµ·
    -0.27
    afc
    -0.26
    æľĪ以æĿ¥
    -0.25
    端æŃ£
    -0.25
     kèm
    -0.25
     length
    -0.25
    ÑĢÑĥж
    -0.24
     cosy
    -0.24
    POSITIVE LOGITS
    éª
    0.26
    æĭħ忧
    0.26
    æķĻ导
    0.25
     {}));↵
    0.25
     Prec
    0.24
    ves
    0.24
    ç»ıå¼Ģ
    0.24
    ä¹Łä¸įä¾ĭå¤ĸ
    0.24
    ownt
    0.23
    IJľ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.