© 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. 111429
    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
    æį¢æĿ¥
    -0.29
    ä¸ĢèĦļ
    -0.25
    èµĦæł¼
    -0.25
    åĪĨåĮĸ
    -0.24
     Teresa
    -0.24
    aby
    -0.24
    éŀł
    -0.24
    èĤ©èĨĢ
    -0.24
    é¢łè¦Ĩ
    -0.24
    èijĹ
    -0.23
    POSITIVE LOGITS
     liner
    0.29
    ::::::
    0.24
     pare
    0.24
     Roku
    0.24
    ynes
    0.24
    -shot
    0.23
     pix
    0.23
    atsu
    0.23
     Plus
    0.23
    ropic
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.