© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7762
    Prev
    Next
    INDEX
    Explanations

    game titles or events

    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
    åIJ¬åIJ¬
    -0.10
    ç¢ĵ
    -0.10
    éŀł
    -0.10
    æ¹Ł
    -0.09
    è¾Ł
    -0.09
    imestamp
    -0.09
    aned
    -0.09
    æĮ¥æīĭ
    -0.09
    èĶ«
    -0.09
    неÑĨ
    -0.09
    POSITIVE LOGITS
    寻
    0.10
    线ä¸ĭ
    0.09
    elter
    0.09
    è§ħ
    0.09
    pany
    0.09
    æŃ¥è¡Į
    0.09
    éĩİå¤ĸ
    0.09
     outdoor
    0.08
    æ½®
    0.08
     ge
    0.08
    Activations Density 0.089%

    No Known Activations