© 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. 97952
    Prev
    Next
    INDEX
    Explanations

    sports

    np_max-act · gemini-2.0-flash
    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
    åī©ä¸ĭçļĦ
    -0.34
    añ
    -0.31
     Pee
    -0.30
    tf
    -0.27
     torn
    -0.26
    tion
    -0.26
     remaining
    -0.25
    urai
    -0.25
    WithError
    -0.25
     rest
    -0.24
    POSITIVE LOGITS
    umpt
    0.28
     AppModule
    0.28
    umption
    0.27
     BaseController
    0.27
     verbosity
    0.26
    帽
    0.25
    ktop
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    é¢Ŀ
    0.24
    aped
    0.24
    Activations Density 0.018%

    No Known Activations