© 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. 49186
    Prev
    Next
    INDEX
    Explanations

    proper names

    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
     mẽ
    -0.10
    ish
    -0.09
     Santiago
    -0.09
    çĵ£
    -0.08
    ishment
    -0.08
     jour
    -0.08
    adic
    -0.08
     никÑĤо
    -0.08
     ÑģвеÑĤ
    -0.08
    ishly
    -0.08
    POSITIVE LOGITS
    ental
    0.10
    utor
    0.10
    çħ
    0.09
    ä¹İ
    0.09
    ÑģÑĤÑĢоен
    0.09
    ÙĪغ
    0.09
    马æĭīæĿ¾
    0.09
    gly
    0.09
    gerald
    0.09
    å²
    0.08
    Activations Density 0.014%

    No Known Activations