© 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. 38708
    Prev
    Next
    INDEX
    Explanations

    carcinogens and chemicals

    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
    (cli
    -0.10
    gio
    -0.10
    èµ°åħ¥
    -0.09
    离ä¸įå¼Ģ
    -0.09
    راس
    -0.09
    æ¡ĪåŃIJ
    -0.09
    离å¼ĢäºĨ
    -0.09
    bolt
    -0.08
     Sens
    -0.08
    éŨæĪ·
    -0.08
    POSITIVE LOGITS
    è¶ĭ
    0.09
    çĶŁåĬ¨
    0.09
    æĹłæķ°
    0.09
     ìĸ´ëłµ
    0.09
    éĻ·éĺ±
    0.08
     pitcher
    0.08
     Vad
    0.08
    fieldname
    0.08
    çī©çIJĨ
    0.08
    rap
    0.08
    Activations Density 0.100%

    No Known Activations