© 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. 57539
    Prev
    Next
    INDEX
    Explanations

    Sakha, Abkhazi, Chechnya

    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
    å²Ļ
    -0.09
    çIJĨä¼ļ
    -0.09
    ç°ĭ
    -0.09
    æijĺ
    -0.08
    erg
    -0.08
    çħ
    -0.08
    ç²®
    -0.08
    filer
    -0.08
    ifie
    -0.08
    èļĢ
    -0.08
    POSITIVE LOGITS
    èħ¿
    0.09
    wig
    0.09
    bane
    0.08
    æīĭæľºåı·
    0.08
    æݾ
    0.08
    æŁ³å·ŀ
    0.08
    æ¨¡æł·
    0.08
    ÙħØŃا
    0.08
    ml
    0.08
    ischer
    0.08
    Activations Density 0.041%

    No Known Activations