© 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. 49746
    Prev
    Next
    INDEX
    Explanations

    gunshot, bullet, or bullets

    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
    äºĮ代
    -0.11
    åĨįè§ģ
    -0.10
    åħ±å»º
    -0.09
    rove
    -0.09
    ä¸įä½ı
    -0.09
    çŃļ
    -0.09
    è¥ŀ
    -0.09
    åįıå®ļ
    -0.09
    åĨ²åĬ¨
    -0.09
    sumer
    -0.09
    POSITIVE LOGITS
    çĹķ迹
    0.11
    çĹķ
    0.10
     loos
    0.08
    迹
    0.08
    æĺ¯å¯¹
    0.08
    Trivia
    0.08
    æŀļ
    0.08
    æĿŀ
    0.08
    纪å§Ķ
    0.08
    åĽ°æī°
    0.08
    Activations Density 0.016%

    No Known Activations