© 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. 50268
    Prev
    Next
    INDEX
    Explanations

    protozoa or parasites

    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
    athers
    -0.10
    åŀĴ
    -0.09
    ignet
    -0.08
    è¾ħ
    -0.08
     Bes
    -0.08
    æĥĬ人
    -0.08
     sill
    -0.08
    neck
    -0.08
    edImage
    -0.08
    ned
    -0.08
    POSITIVE LOGITS
    å¼Ģæ°´
    0.10
     Plum
    0.10
    holes
    0.09
    æĹ¶ä»£çļĦ
    0.09
    åŃij
    0.09
    usher
    0.08
    ä¸ķ
    0.08
    ä¸Ĭåİ»
    0.08
    ائÙĤ
    0.08
    EqualTo
    0.08
    Activations Density 0.008%

    No Known Activations