© 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. 18615
    Prev
    Next
    INDEX
    Explanations

    villanova university college

    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
    ÑģÑĤвеннÑĭй
    -0.09
     ÑĢаÑģÑģмаÑĤÑĢива
    -0.09
    åĮºåĨħ
    -0.09
    æ°´éĩı
    -0.09
    ilion
    -0.09
    é¢ĺ主
    -0.09
    ilden
    -0.08
    éĢ
    -0.08
    ãĤ¨ãĥªãĤ¢
    -0.08
    jang
    -0.08
    POSITIVE LOGITS
    æķħå±ħ
    0.12
    éŃĶæľ¯
    0.09
    嶷
    0.09
    çŁ¥è¯ĨåĪĨåŃIJ
    0.09
    o
    0.09
    ns
    0.08
     Knight
    0.08
    nn
    0.08
    aux
    0.08
    bred
    0.08
    Activations Density 0.001%

    No Known Activations