© 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. 56825
    Prev
    Next
    INDEX
    Explanations

    death and murder crime

    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
    工夫
    -0.12
     ÑĤеÑħнологии
    -0.10
    ersh
    -0.09
     pragma
    -0.09
    åĽŀåİ»
    -0.09
    æĬ±çĿĢ
    -0.09
    @[
    -0.09
    erver
    -0.09
    acea
    -0.09
    åĬŁå¤«
    -0.08
    POSITIVE LOGITS
    çļĦåıijçĶŁ
    0.11
     viá»ĩc
    0.10
    çģŃ亡
    0.10
    è´£ç¼ĸ
    0.10
    adel
    0.09
    èIJ½
    0.09
    çļĦåĪ°æĿ¥
    0.09
    æ´½
    0.09
    éĻ¨
    0.09
    顶
    0.09
    Activations Density 0.141%

    No Known Activations