© 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. 47903
    Prev
    Next
    INDEX
    Explanations

    fleeing from danger or conflict

    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
    ä¸į解
    -0.10
    樽
    -0.10
    çIJī
    -0.10
    getReference
    -0.09
    æİ¥éĢģ
    -0.09
    éħŀ
    -0.09
    è¿Ľåĩºåı£
    -0.09
    è¾ĵéĢģ
    -0.09
    èijŃ
    -0.09
    åŃĺæ´»
    -0.09
    POSITIVE LOGITS
    躲éģ¿
    0.13
    éģ¿å¼Ģ
    0.13
    éĢĥéģ¿
    0.13
    éĢĥ离
    0.13
    躲
    0.12
    éģ¿
    0.11
    åĽŀéģ¿
    0.10
    éĢĢ
    0.09
     khá»ıi
    0.09
    éģ¿ãģij
    0.09
    Activations Density 0.043%

    No Known Activations