© 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. 88111
    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
    éĥ½å¸ĤæĬ¥
    -0.27
    aland
    -0.26
     latter
    -0.25
    確ãģĭ
    -0.25
    geist
    -0.24
     MSS
    -0.24
    tle
    -0.24
     thing
    -0.24
    åĩij
    -0.24
     mr
    -0.23
    POSITIVE LOGITS
    orado
    0.30
     DISP
    0.28
    æĺ¯ä¸įåı¯èĥ½
    0.25
    家åĸ»æĪ·æĻĵ
    0.25
    è·³è·ĥ
    0.24
    é»ijçĻ½
    0.24
    æľĢåħ³éĶ®
    0.24
    _quit
    0.24
    xC
    0.23
    dux
    0.23
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.