© 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. 21899
    Prev
    Next
    INDEX
    Explanations

    the noun

    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
    çļĦ人éĥ½
    -0.08
    å°±è¿Ļä¹Ī
    -0.08
    æŃ£åľ¨è¿Ľè¡Į
    -0.07
    åŃIJéĩĮ
    -0.07
    åĬ³åĬ¨
    -0.07
    åIJĦç§į
    -0.07
    cluding
    -0.07
     ÑĢеÑĪа
    -0.07
     именно
    -0.07
    åħ
    -0.07
    POSITIVE LOGITS
    è¹Ī
    0.10
    apesh
    0.09
    quin
    0.09
    çĦ±
    0.09
     سبÙĬÙĦ
    0.08
    ä¼ļéķ¿
    0.08
    æĹłå¥Ī
    0.08
     ë¶Ī구íķĺê³ł
    0.08
    å¨ł
    0.08
    onte
    0.08
    Activations Density 0.396%

    No Known Activations