© 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. 130765
    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
    便ä¼ļ
    -0.23
    ãĤ¬ãĤ¤
    -0.23
     contrat
    -0.23
    åı²ä¸Ĭ
    -0.22
     charter
    -0.22
     doGet
    -0.22
    apor
    -0.22
     anonymously
    -0.22
    sett
    -0.21
    credits
    -0.21
    POSITIVE LOGITS
    amina
    0.24
    çľģå§Ķ
    0.23
    ç¿¡ç¿ł
    0.22
    .ua
    0.21
    大人
    0.21
    æĶ¯æĮģ
    0.21
    ="?
    0.20
    åľ¨
    0.20
    -ves
    0.20
    dbl
    0.20
    Activations Density 0.347%

    No Known Activations

    This feature has no known activations.