© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19766
    Prev
    Next
    INDEX
    Explanations

    st and -first century

    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
    åıįé¦Ī
    -0.10
    éĥ¢
    -0.09
     boosted
    -0.09
    éĤĪ
    -0.09
    lessly
    -0.09
    è¡·
    -0.08
     telegram
    -0.08
    acked
    -0.08
    ugin
    -0.08
    .Ptr
    -0.08
    POSITIVE LOGITS
    äº²çľ¼
    0.10
    eya
    0.09
    éĬ®
    0.09
    ç¼Ĵ
    0.09
    殿
    0.09
    æľªå©ļ
    0.09
    åŁİå¸Ĥ群
    0.09
     оÑĤмеÑĤ
    0.09
    æĪ·ç±į
    0.08
     Cousins
    0.08
    Activations Density 0.017%

    No Known Activations