© 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. 112171
    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
    æĬµæĬĹåĬĽ
    -0.28
    ittal
    -0.27
    acent
    -0.25
    iscrim
    -0.24
     circ
    -0.24
     resolve
    -0.23
    ä¸Ģ个æĺ¯
    -0.23
    getConnection
    -0.23
    isseur
    -0.23
    ç²Ĵ
    -0.23
    POSITIVE LOGITS
    kke
    0.25
    è¿ĻäºĽéĹ®é¢ĺ
    0.25
    -mouth
    0.24
    elder
    0.24
    ivia
    0.23
    eller
    0.23
    èĢĮåľ¨
    0.23
    annis
    0.23
    ↵ ↵
    0.23
    ingham
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.