© 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. 111892
    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
     Harrison
    -0.28
     gh
    -0.27
     inc
    -0.27
     GI
    -0.26
     downs
    -0.24
     mid
    -0.24
    ç«ĭãģ¡
    -0.24
    itim
    -0.23
    orias
    -0.23
    ]|[
    -0.23
    POSITIVE LOGITS
     iota
    0.29
    åľ¨å¸Ĥåľºä¸Ĭ
    0.24
    tern
    0.24
    appings
    0.24
    延éķ¿
    0.24
    ä»ħ代表
    0.24
    YTE
    0.24
    avigation
    0.23
    Qualifier
    0.23
    æ¡£
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.