© 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. 36391
    Prev
    Next
    INDEX
    Explanations

    talk about

    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
    æģ£
    -0.09
    aley
    -0.08
    ä¹īåĬ¡
    -0.08
    _MUX
    -0.08
     Cul
    -0.08
    鸢
    -0.08
    çļĦ人çī©
    -0.08
    æģĻ
    -0.08
    女ç¥ŀ
    -0.08
    MET
    -0.08
    POSITIVE LOGITS
    è°Ī论
    0.16
    è°Ī
    0.14
    讨论
    0.13
     talk
    0.12
     discuss
    0.11
    è¨İè«ĸ
    0.11
     conversations
    0.11
     discussion
    0.11
    è¯Ŀé¢ĺ
    0.11
    æ´¥
    0.11
    Activations Density 0.106%

    No Known Activations