© 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. 5243
    Prev
    Next
    INDEX
    Explanations

    Join us or help

    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
    éĻĨ
    -0.09
     пÑĢедоÑģÑĤ
    -0.09
    лев
    -0.09
    æ·±åĪĩ
    -0.08
    åŃĺæ´»
    -0.08
    æĤĸ
    -0.08
    æįķæįī
    -0.08
    .azure
    -0.08
    åIJ¯è¿ª
    -0.08
    åıijçİ°èĩªå·±
    -0.08
    POSITIVE LOGITS
    丢äºĨ
    0.09
    ç£Ĭ
    0.09
    uitive
    0.08
    [email
    0.08
    _DP
    0.08
    èĦ±åıij
    0.08
    amt
    0.08
    æĸ¹åľĨ
    0.07
    大åıij
    0.07
    decltype
    0.07
    Activations Density 0.011%

    No Known Activations