© 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. 35902
    Prev
    Next
    INDEX
    Explanations

    vul, vulgar, vulvar, vulgaris, vulcanology

    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
    æįİ
    -0.11
    ably
    -0.09
    aran
    -0.09
     пок
    -0.08
     Wan
    -0.08
    åŀ£
    -0.08
    inals
    -0.08
    몽
    -0.08
    oya
    -0.08
    OID
    -0.08
    POSITIVE LOGITS
    aison
    0.11
    缯
    0.10
    äºĨèĩªå·±çļĦ
    0.10
    atform
    0.10
    ãģ¾ãģ¾
    0.09
    ÑĥÑİÑĤ
    0.09
    ês
    0.09
    низ
    0.08
     kra
    0.08
    ä¸Ģç¯ĩ
    0.08
    Activations Density 0.003%

    No Known Activations