© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51115
    Prev
    Next
    INDEX
    Explanations

    do not edit

    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
    onis
    -0.10
    俯
    -0.09
    æ°¸ä¸į
    -0.09
    cond
    -0.09
    Cond
    -0.09
    bes
    -0.09
    åľ¨è¿Ļ
    -0.09
     eclipse
    -0.09
    clipse
    -0.08
    è¶ħé¢Ŀ
    -0.08
    POSITIVE LOGITS
    åĬĽæ°Ķ
    0.11
    éĵĻ
    0.09
    éĿ´
    0.08
    رÙĤ
    0.08
    è´¡çĮ®
    0.08
    æľ¬äºĭ
    0.08
    illas
    0.08
    ç»ĨåĮĸ
    0.08
    ำ
    0.08
    ãĥĨãĥ³
    0.08
    Activations Density 0.040%

    No Known Activations