© 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. 17384
    Prev
    Next
    INDEX
    Explanations

    sexual offenders

    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
    æįŁä¼¤
    -0.11
    æķıéĶIJ
    -0.10
    odox
    -0.10
    ç³Ĭ
    -0.09
    éģŃ
    -0.09
    acin
    -0.09
    å¨ĺ家
    -0.09
    åıĹæįŁ
    -0.09
     prem
    -0.09
    æĻļæĬ¥
    -0.09
    POSITIVE LOGITS
    å¨Ī
    0.11
    ή
    0.09
     predator
    0.09
    ä½ľæ¡Ī
    0.09
    ogene
    0.09
    è¡Į为
    0.09
    鬲
    0.09
    ÑĤели
    0.09
    æĿĢ人
    0.08
    æ½ľ
    0.08
    Activations Density 0.119%

    No Known Activations