© 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. 11656
    Prev
    Next
    INDEX
    Explanations

    cycling races

    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
    çĮ¾
    -0.09
    åħļçļĦåįģä¹Ŀ
    -0.09
    åĴĮè°IJ
    -0.09
    urt
    -0.09
    çĮ¥
    -0.09
     Cobra
    -0.09
    cobra
    -0.08
    æĹı群
    -0.08
    vio
    -0.08
    ç¼Ń
    -0.08
    POSITIVE LOGITS
    èį£å¹¸
    0.09
    æĸ°äº¬
    0.09
     Ridley
    0.08
     صÙģ
    0.08
    åĩºè·¯
    0.08
    emon
    0.08
    fect
    0.08
    etti
    0.08
    acement
    0.08
    empo
    0.08
    Activations Density 0.093%

    No Known Activations