© 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. 19330
    Prev
    Next
    INDEX
    Explanations

    peanut butter and bars

    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
    edList
    -0.10
    æ±īåŃIJ
    -0.09
    ãĢħ
    -0.09
    \Collections
    -0.09
    æĸ°è¥¿
    -0.09
    çĶµåŃIJä¿¡æģ¯
    -0.09
    äºĮ代
    -0.09
    enstein
    -0.09
    odash
    -0.09
    opsis
    -0.08
    POSITIVE LOGITS
    èľ©
    0.09
     Moss
    0.09
    ä¾Ŀæ³ķ
    0.09
    ä¼łæĴŃ
    0.08
     Vig
    0.08
    вл
    0.08
    Editable
    0.08
    fect
    0.08
    人éĢī
    0.08
    acking
    0.08
    Activations Density 0.004%

    No Known Activations