© 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. 97464
    Prev
    Next
    INDEX
    Explanations

    Importance of something

    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
    ogle
    -0.27
    mer
    -0.27
    osopher
    -0.26
    æĽĽ
    -0.25
    åı¦ä¸Ģç§į
    -0.25
    -rights
    -0.24
    ibles
    -0.24
    è§ļ
    -0.24
    ycler
    -0.24
     Anc
    -0.23
    POSITIVE LOGITS
    çīĮ
    0.27
    CEL
    0.26
     humility
    0.25
    åĿļæĮģä¸įæĩĪ
    0.25
    端æŃ£
    0.25
    nez
    0.25
    inders
    0.25
    大éĿ¢ç§¯
    0.24
    åŃľ
    0.24
    acha
    0.24
    Activations Density 0.003%

    No Known Activations