© 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. 129732
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    enet
    -0.28
    iri
    -0.28
     unless
    -0.26
    JI
    -0.25
     palms
    -0.25
    èģĶç½ij
    -0.25
    _SI
    -0.24
    APS
    -0.24
    SI
    -0.24
     Ùħج
    -0.24
    POSITIVE LOGITS
     various
    0.76
    åIJĦç§į
    0.67
    ä¸įåIJĮçļĦ
    0.62
     Various
    0.61
     different
    0.59
    çļĦåIJĦç§į
    0.58
    ä¸įåIJĮ
    0.57
    Various
    0.57
    çļĦä¸įåIJĮ
    0.55
    åIJĦ種
    0.54
    Activations Density 0.038%

    No Known Activations