© 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. 21422
    Prev
    Next
    INDEX
    Explanations

    affirmative answers

    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
    loth
    -0.09
    ActionCreators
    -0.09
    astle
    -0.09
    ény
    -0.09
    iani
    -0.08
    меÑģÑĤ
    -0.08
    ollection
    -0.08
    rians
    -0.08
    vice
    -0.08
    稿
    -0.08
    POSITIVE LOGITS
    ä¸Ģ件äºĭ
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    忱
    0.09
    èŀ³
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    æ²Ń
    0.08
    个å¤ļ
    0.08
    æ¶Ķ
    0.08
    ä¸ĩä¸Ģ
    0.08
    Datum
    0.08
    Activations Density 0.022%

    No Known Activations