© 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. 111766
    Prev
    Next
    INDEX
    Explanations

    Pink

    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
    å°Ķæĸ¯
    -0.31
    线ä¸Ĭ
    -0.30
    abs
    -0.28
    IEWS
    -0.27
    resher
    -0.26
     recap
    -0.26
    åĤĴ
    -0.26
     Cou
    -0.25
    æĽ´ä½İ
    -0.25
     reflection
    -0.25
    POSITIVE LOGITS
    解å¼Ģ
    0.27
    itted
    0.24
     tolerant
    0.24
    éķ¿çŁŃ
    0.24
    оÑĩно
    0.24
     ));↵
    0.23
     gathering
    0.23
    dorf
    0.23
    Implemented
    0.23
     ))↵
    0.23
    Activations Density 0.027%

    No Known Activations