© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59101
    Prev
    Next
    INDEX
    Explanations

    wiki link internal

    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
    æ±Łä¸ľ
    -0.11
    uder
    -0.10
    麻çĹ¹
    -0.09
    apat
    -0.09
    æĺİæĺ¾çļĦ
    -0.09
    ä¿Ŀè´¹
    -0.09
    æµģéĢĿ
    -0.08
    åį°è±¡æ·±åĪ»
    -0.08
    çİ°åĩº
    -0.08
    èĤ¡ä¸ľå¤§ä¼ļ
    -0.08
    POSITIVE LOGITS
    bian
    0.09
    ä¸įåIJĮ
    0.08
    ocratic
    0.08
    å§ĵ
    0.08
    itol
    0.08
    å·²ä¹ħçļĦ
    0.08
    aded
    0.08
     Mej
    0.08
    çī¹èī²çļĦ
    0.08
    é¢ĨåŁŁçļĦ
    0.07
    Activations Density 0.207%

    No Known Activations