© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162352
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļåıª
    -0.29
    åıĹ访èĢħ
    -0.28
    åıĹ访
    -0.27
    inue
    -0.27
    biz
    -0.27
    var
    -0.26
    åĢ¾
    -0.25
     researched
    -0.25
    èIJ¥
    -0.25
    èIJ¥åľ°
    -0.25
    POSITIVE LOGITS
    geh
    0.29
     near
    0.28
    ellow
    0.27
    achusetts
    0.26
    ockey
    0.26
    åľ¨æĹ¥æľ¬
    0.26
    auce
    0.24
    ç³»ç»ŁçļĦ
    0.24
    еÑģÑĤво
    0.24
    Near
    0.24
    Activations Density 0.007%

    No Known Activations