© 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. 31350
    Prev
    Next
    INDEX
    Explanations

    Ask, Art, DOCTYPE, tests, stress

    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
    æİĮæı¡äºĨ
    -0.10
     dispar
    -0.09
     horns
    -0.09
    fir
    -0.09
     thÆ°Æ¡ng
    -0.09
    ä¹ĥ
    -0.09
    kest
    -0.09
    zem
    -0.09
    .coord
    -0.08
    ÑģеÑĤ
    -0.08
    POSITIVE LOGITS
    åĵº
    0.10
    é¡¿æŶ
    0.09
    æĪĺçķ¥æĢ§
    0.09
    imes
    0.08
    ç´§è·Ł
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
    åijĭ
    0.08
    èIJİ
    0.08
     Charleston
    0.08
    使人
    0.08
    Activations Density 0.001%

    No Known Activations