© 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. 49978
    Prev
    Next
    INDEX
    Explanations

    killer committing violence

    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
    åķĨ
    -0.09
    æ»Ł
    -0.09
    辨
    -0.08
    assis
    -0.08
    Mutable
    -0.08
     tast
    -0.08
    éĽ³
    -0.08
    ertas
    -0.08
    mere
    -0.08
     Bair
    -0.08
    POSITIVE LOGITS
    ä¸Ģè·¯
    0.11
    ä¹¾åĿ¤
    0.10
    åī²
    0.10
    æĬĬèĩªå·±
    0.10
    èĩªæĿĢ
    0.10
    дей
    0.10
    hide
    0.10
    åĦĴ家
    0.09
    éķ¿çŁŃ
    0.09
    åIJ¼
    0.09
    Activations Density 0.063%

    No Known Activations