© 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. 98456
    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
     projects
    -0.29
     halves
    -0.27
    ``
    -0.26
    Text
    -0.25
     Style
    -0.25
    styles
    -0.25
    faker
    -0.25
    確ãģĭãģ«
    -0.24
    ÑĤок
    -0.24
    AP
    -0.24
    POSITIVE LOGITS
    ioned
    0.28
     prostit
    0.26
    redni
    0.26
    bow
    0.26
    åIJ¬å¾Ĺ
    0.25
    æĺĶæĹ¥
    0.25
    é¢ī
    0.25
    izr
    0.24
    ered
    0.24
    skins
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.