© 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. 16932
    Prev
    Next
    INDEX
    Explanations

    premier / premiere

    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
    olum
    -0.10
    çļĦä¸Ģ项
    -0.10
    ãģ®ãģĵãģ¨
    -0.09
    Msp
    -0.09
    startup
    -0.09
    æĸ¹éĴĪ
    -0.09
    zik
    -0.09
    åIJĦ项
    -0.09
    çĥ¦èºģ
    -0.08
    UNKNOWN
    -0.08
    POSITIVE LOGITS
    åľ°æ®µ
    0.14
    -tier
    0.12
    ç²¾èĭ±
    0.11
    -quality
    0.11
    æĹłæ¯Ķ
    0.10
    è´¨éĩıåĴĮ
    0.10
    äºijéĽĨ
    0.10
    éĥ¨ä½į
    0.09
    quality
    0.09
    çĶļ
    0.09
    Activations Density 0.132%

    No Known Activations