© 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. 130329
    Prev
    Next
    INDEX
    Explanations

    Common English phrases

    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
    好åıĭ
    -0.38
    åIJĪä½ľä¼Ļä¼´
    -0.34
    ç«ŀäºī对æīĭ
    -0.33
    çŁ¥å·±
    -0.33
    ç»Ļèĩªå·±
    -0.33
     companions
    -0.32
    对èĩªå·±
    -0.32
     companion
    -0.32
     neighbours
    -0.32
     дÑĢÑĥзÑĮÑı
    -0.29
    POSITIVE LOGITS
    IPH
    0.25
     Freeman
    0.25
    xyz
    0.24
    è¾¹
    0.24
    WithTitle
    0.24
    iable
    0.24
    è¾Ł
    0.23
    olatile
    0.23
    @Xml
    0.23
    é³³
    0.23
    Activations Density 0.002%

    No Known Activations