© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    holistic, nonlinear, qualitative

    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
    неж
    -0.08
     {}.
    -0.08
    klär
    -0.08
     ges
    -0.08
    ÑĤол
    -0.08
     Cly
    -0.08
    langs
    -0.08
    once
    -0.08
    awy
    -0.07
    lm
    -0.07
    POSITIVE LOGITS
    æ¡ħ
    0.11
    é«ĺçļĦ
    0.11
    åIJİèĢħ
    0.10
    ìłģìĿ¸
    0.10
    主ä¹īèĢħ
    0.10
    è¾Ĺ
    0.10
    åı¦ä¸Ģè¾¹
    0.10
    åŀ©
    0.10
    æĢ§çļĦ
    0.10
    主義
    0.09
    Activations Density 0.017%

    No Known Activations