© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    emigrated from

    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
    asco
    -0.10
    ivate
    -0.09
    éĩį
    -0.09
     ÑģкаÑĩаÑĤÑĮ
    -0.08
    éĥİ
    -0.08
    åŃ©
    -0.08
    èļ¤
    -0.08
    fcn
    -0.08
    è°³
    -0.08
    éĤ
    -0.08
    POSITIVE LOGITS
    åħ¨å¤©
    0.11
    RIPT
    0.09
    çļĩåIJİ
    0.09
    -UA
    0.09
    plements
    0.09
    è¥ģ
    0.08
    íĺij
    0.08
    Opp
    0.08
    ä¸įåĪĨ
    0.08
    urai
    0.08
    Activations Density 0.070%

    No Known Activations