© 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. 50067
    Prev
    Next
    INDEX
    Explanations

    physical assault or action

    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
    åĩºæ¸¸
    -0.11
    èµĦ
    -0.10
    éĢIJ
    -0.09
    çĬĴ
    -0.09
    å¨ĺ家
    -0.09
    åķ¬
    -0.09
    åįĪåIJİ
    -0.09
    éŁ¿
    -0.09
    éĵ¢
    -0.09
    宿
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.10
    åĪ®
    0.10
    æİIJ
    0.10
    æİ´
    0.10
     physically
    0.10
    çī©çIJĨåѦ
    0.10
    çī©çIJĨ
    0.09
    lasses
    0.09
    lass
    0.09
    追赶
    0.09
    Activations Density 0.140%

    No Known Activations