© 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. 12-TRANSCODER-HP
    7. 23670
    Prev
    Next
    INDEX
    Explanations

    Brutality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eref
    -0.29
    å¨ģ
    -0.28
    éī´
    -0.26
    ération
    -0.25
     simult
    -0.25
    abbr
    -0.25
    æĽ¿æį¢
    -0.24
    иÑĢование
    -0.24
    ï¼īï¼Į
    -0.24
     Filed
    -0.24
    POSITIVE LOGITS
    _odd
    0.28
    æĦŁ
    0.28
    éģĬ
    0.26
    ಡ
    0.25
    [,]
    0.24
    ä¹Łä¸įæķ¢
    0.24
    ArrayOf
    0.24
    æĦŁåºĶ
    0.24
    ocre
    0.24
    æĩĤå¾Ĺ
    0.23
    Activations Density 0.020%

    No Known Activations