© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    hymenopterans, insects

    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
    è¯Ĥ
    -0.09
    ä¼Ļ
    -0.09
     kra
    -0.08
     mil
    -0.08
    .EOF
    -0.08
    ied
    -0.08
    åĨķ
    -0.08
    loo
    -0.07
    AttributeValue
    -0.07
    ings
    -0.07
    POSITIVE LOGITS
    eer
    0.10
    uous
    0.10
    è§ļ
    0.10
    Ã¼ÅŁ
    0.09
    reon
    0.09
    ÑĢÑİ
    0.09
    Ø·ÙĨ
    0.09
     liá»ĩt
    0.09
     originals
    0.09
    /accounts
    0.09
    Activations Density 0.003%

    No Known Activations