© 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. 18917
    Prev
    Next
    INDEX
    Explanations

    protein binding and inhibitory factors

    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
    èĢģ大
    -0.09
    azi
    -0.09
    ç¬Ĩ
    -0.09
     Beng
    -0.08
    åģļåĩºäºĨ
    -0.08
     дело
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
    ROS
    -0.08
     mush
    -0.08
     pron
    -0.08
    POSITIVE LOGITS
    éĨ´
    0.10
    éĶī
    0.09
    ä¸į足
    0.09
     недо
    0.09
     furnish
    0.09
    .cancel
    0.09
    æĶ¿æ³ķ
    0.09
    otta
    0.09
    輩
    0.08
    åħĨ
    0.08
    Activations Density 0.862%

    No Known Activations