© 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. 60986
    Prev
    Next
    INDEX
    Explanations

    abuse and torture

    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
    åij±
    -0.10
    èĩªå·±
    -0.09
    éĵĤ
    -0.09
    ounce
    -0.09
    ä¼Ĺ人
    -0.08
    åħ·æľīèī¯å¥½
    -0.08
    rots
    -0.08
    goo
    -0.08
    æ¯ı人
    -0.08
     Chaos
    -0.08
    POSITIVE LOGITS
    æѧè§Ĩ
    0.12
    å¼Ģå§ĭäºĨ
    0.12
    æīĵåİĭ
    0.11
    ä¸įåħ¬å¹³
    0.10
    æĬ¬å¤´
    0.09
    åİĭåĪ¶
    0.09
     intimidation
    0.09
    å®ļåIJij
    0.09
    æ¬ºè´Ł
    0.09
    严åİī
    0.08
    Activations Density 0.079%

    No Known Activations