© 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. 48942
    Prev
    Next
    INDEX
    Explanations

    natural science education

    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
    åĮ»çĸĹ
    -0.08
     medical
    -0.07
    UST
    -0.07
    _AST
    -0.07
    _tok
    -0.07
    å¼Ĥ
    -0.07
     Medical
    -0.07
    ainment
    -0.07
    Medical
    -0.07
     Dag
    -0.07
    POSITIVE LOGITS
    ä¿ĿæĬ¤åĮº
    0.13
    èĩªçĦ¶ä¿ĿæĬ¤
    0.13
    çī©ç§į
    0.12
    éĩİå¤ĸ
    0.12
    éĩİçĶŁ
    0.11
    çĶŁæĢģæĸĩæĺİ
    0.11
    éĩİçĶŁåĬ¨çī©
    0.11
    çĶŁæĢģ
    0.11
     Wildlife
    0.11
    ç§ijæĻ®
    0.10
    Activations Density 0.260%

    No Known Activations