© 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. 18698
    Prev
    Next
    INDEX
    Explanations

    killing animals

    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
    åį·
    -0.11
     Lair
    -0.10
     Exhaust
    -0.09
    ä¿
    -0.09
    éĿ¡
    -0.08
    yer
    -0.08
    inia
    -0.08
    urch
    -0.08
    haust
    -0.08
    Sharper
    -0.08
    POSITIVE LOGITS
    èµIJ
    0.11
    æĿĢæŃ»
    0.11
    å¹²é¢Ħ
    0.10
    åįŀ
    0.10
    ä»ĭåħ¥
    0.10
    åĶ¯æľī
    0.10
    éĥ¨ä»½
    0.10
    å¤ļä½ĻçļĦ
    0.09
    æĹłçº¿çĶµ
    0.09
    æĦ¿æĻ¯
    0.09
    Activations Density 0.068%

    No Known Activations