© 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. 54266
    Prev
    Next
    INDEX
    Explanations

    offers

    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
    åĽ·
    -0.11
    æĵį
    -0.09
    éĻįåĪ°
    -0.09
    æĪIJç«ĭäºĨ
    -0.09
    Brightness
    -0.09
    åĵĢ
    -0.09
    imen
    -0.09
     continent
    -0.09
    å¿ĺè®°äºĨ
    -0.08
    ucky
    -0.08
    POSITIVE LOGITS
    ings
    0.10
    çļĦä¸ĢåĪĩ
    0.10
    bour
    0.09
    äºĨä¸Ģ个
    0.09
    äºĨä¸Ģ
    0.08
    ial
    0.08
    æŀģ大çļĦ
    0.08
    à¹Ĥà¸Ńà¸ģาส
    0.08
    楷
    0.08
    带æĿ¥
    0.08
    Activations Density 0.024%

    No Known Activations