© 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. 17270
    Prev
    Next
    INDEX
    Explanations

    criminal acts or roles

    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
    æħĪ
    -0.11
    .ali
    -0.10
    ç²¾åįİ
    -0.10
    鹧
    -0.09
     knobs
    -0.09
    òng
    -0.09
    壯
    -0.09
    èµĦ管
    -0.08
    讶
    -0.08
    亲çĪ±
    -0.08
    POSITIVE LOGITS
    ule
    0.09
    éĢĢå¸Ĥ
    0.09
    踪
    0.08
    uality
    0.08
    æīĭä¸ĭ
    0.08
    ä¸įèĤ¯
    0.08
    çݰ象
    0.08
    çĹķ
    0.08
    æ¯ı次éĥ½
    0.08
    tent
    0.08
    Activations Density 0.060%

    No Known Activations