© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    group or company affiliation

    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
    edBy
    -0.09
    èĻij
    -0.09
    许åı¯
    -0.08
    çŃ¹
    -0.08
    æĮ¡
    -0.08
     yell
    -0.08
    íĹĮ
    -0.08
    æħ·
    -0.08
    è¿ĺåľ¨
    -0.08
    stro
    -0.08
    POSITIVE LOGITS
    æݧèĤ¡éĽĨåĽ¢
    0.11
    å´©
    0.10
    anca
    0.09
    çľĭä¸įè§ģ
    0.09
    æݧèĤ¡
    0.09
    åĽ«
    0.09
    æļĩ
    0.09
    åĪ°ä½į
    0.09
    ermann
    0.09
    æİĮæݧ
    0.09
    Activations Density 0.096%

    No Known Activations