© 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. 112683
    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
     Portal
    -0.27
     caller
    -0.27
    éļıæŶ
    -0.26
     electric
    -0.26
    马ä¸Ĭ
    -0.26
     wherever
    -0.26
    æĹłè®ºå¦Ĥä½ķ
    -0.26
    åı¦ä¸ĢåįĬ
    -0.25
    æĸ¤
    -0.25
     whatever
    -0.25
    POSITIVE LOGITS
    attention
    0.27
    plevel
    0.25
    als
    0.25
     stor
    0.25
    ovic
    0.24
    æĢ§çĸ¾çĹħ
    0.24
    jos
    0.24
    讲
    0.23
    _ESCAPE
    0.23
     writeFile
    0.23
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.