© 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. 32333
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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
    éļĶçĿĢ
    -0.09
    溯
    -0.09
    LOC
    -0.09
    å±ıå¹ķä¸Ĭ
    -0.09
    åĩºçīĪ社
    -0.09
    å¹¹
    -0.09
    绶
    -0.08
    éĴ¢æĿ¿
    -0.08
    setTimeout
    -0.08
    èµİ
    -0.08
    POSITIVE LOGITS
    åħįè´¹
    0.18
     беÑģплаÑĤно
    0.15
     free
    0.14
    FREE
    0.14
     gratuito
    0.13
    free
    0.13
    åħįè²»
    0.13
    _free
    0.13
    çĦ¡æĸĻ
    0.12
     gratuitement
    0.12
    Activations Density 0.126%

    No Known Activations