© 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. 87230
    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
    зал
    -0.26
    å¹Į
    -0.24
    films
    -0.24
     adultes
    -0.24
    å°Ŀè¯ķ
    -0.24
    è¿Ļ家åħ¬åı¸
    -0.24
     initialise
    -0.23
     Blackjack
    -0.23
     intox
    -0.23
    _fil
    -0.23
    POSITIVE LOGITS
    èį¡
    0.29
    cci
    0.27
    0.26
    .ext
    0.26
    buch
    0.26
    æĶ¹éĿ©
    0.26
    erv
    0.26
    ç¥ŀç§ĺ
    0.25
    ä¿®
    0.25
    å¼ķ
    0.25
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.