© 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. 7149
    Prev
    Next
    INDEX
    Explanations

    canceled, never, unpublished, terminated, rejected

    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
    ä¸Ģä¸ĭåŃIJå°±
    -0.12
    æĦĪ
    -0.11
    åĪļåĪļ
    -0.10
    è¢Ĵ
    -0.09
    ä¸įæĸŃå¢ŀåĬł
    -0.09
    éĻį
    -0.09
    _SPECIAL
    -0.09
     popcorn
    -0.09
    éĢĢå¸Ĥ
    -0.09
    è¶Ĭæĺ¯
    -0.09
    POSITIVE LOGITS
    æľªæĪIJ
    0.19
    æľªèĥ½
    0.15
    没èĥ½
    0.13
    æľª
    0.13
     ÙĪÙĦÙħ
    0.11
    æľĢç»Ī
    0.11
     never
    0.11
     olmad
    0.10
    ç»Ī究
    0.10
    æľªæĽ¾
    0.10
    Activations Density 0.152%

    No Known Activations