© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    doom, half-life, engine, quake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĻ¨
    -0.09
    lea
    -0.09
    æ¸ħæĻ¨
    -0.09
    庶
    -0.08
    åĿIJèIJ½
    -0.08
    çIJħ
    -0.08
    çĿ«æ¯Ľ
    -0.08
    ç°Ł
    -0.08
    udo
    -0.08
    çŃĸ
    -0.08
    POSITIVE LOGITS
    HOOK
    0.10
    wich
    0.09
    æŃ¥
    0.09
    æ»ı
    0.09
    æı¡
    0.09
    ä»ĸ说
    0.09
     ÐŃÑĤ
    0.08
     tiên
    0.08
    åı£è¢ĭ
    0.08
    .MEDIA
    0.08
    Activations Density 0.032%

    No Known Activations