© 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. 97996
    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
    bes
    -0.29
    fac
    -0.26
    æIJĢ
    -0.25
    åĢŁãĤĬ
    -0.25
    enberg
    -0.25
    ä¹Łå¥½
    -0.24
    ä¸įå®ļ
    -0.24
    sect
    -0.24
     Slut
    -0.24
    borrow
    -0.24
    POSITIVE LOGITS
     setDescription
    0.26
    ork
    0.24
     Fred
    0.24
     Hall
    0.24
     Mark
    0.23
    çķĮ第ä¸Ģ
    0.23
    éªĤ
    0.23
    eated
    0.23
    è´§è¿IJ
    0.23
    urray
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.