© 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. 111695
    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
    å¾Īä½İ
    -0.26
    encing
    -0.26
    æŀŃ
    -0.25
    hall
    -0.25
    ä¼ģä¸ļåľ¨
    -0.24
    å¾Īé«ĺ
    -0.24
    ¶Ī
    -0.24
    -neck
    -0.23
     Bands
    -0.23
    .cursor
    -0.23
    POSITIVE LOGITS
    translated
    0.26
    olith
    0.26
    UILTIN
    0.25
    ypsy
    0.25
    对æĸ¹
    0.25
    apyrus
    0.25
    ypress
    0.24
    xcf
    0.24
    Translated
    0.24
    ublish
    0.24
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.