© 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. 4851
    Prev
    Next
    INDEX
    Explanations

    search terms, image, flexible, activity

    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
    кал
    -0.11
    èĽĶ
    -0.09
    å¥īçĮ®
    -0.09
    罡
    -0.09
    uai
    -0.08
    Õª
    -0.08
    å¹³åĿĩæ°´å¹³
    -0.08
    alic
    -0.08
     Sext
    -0.08
    æѸ
    -0.08
    POSITIVE LOGITS
    è¶Ĭ好
    0.09
    dition
    0.08
    ossier
    0.08
     fond
    0.08
     Fond
    0.08
    аÑĤÑĥÑĢ
    0.08
    éģ¿å¼Ģ
    0.08
    æĭ¦
    0.08
    åŁºéĩij
    0.08
    Fallback
    0.08
    Activations Density 0.011%

    No Known Activations