© 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. 62926
    Prev
    Next
    INDEX
    Explanations

    age and experience

    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
    活泼
    -0.10
    åѱ
    -0.10
    éĢģåĩº
    -0.10
    åİĮæģ¶
    -0.09
    æģ¶
    -0.09
    纤
    -0.09
    延伸
    -0.09
    ç±
    -0.09
    è¶ģçĿĢ
    -0.09
    è¿İåIJĪ
    -0.09
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.21
    æĪIJçĨŁçļĦ
    0.18
    ç»ıéªĮ丰å¯Į
    0.18
     mature
    0.17
    ç»ıéªĮ
    0.16
    éĺħåİĨ
    0.15
     Mature
    0.15
     seasoned
    0.15
    ç»ıéªĮåĴĮ
    0.15
    èĢģ
    0.14
    Activations Density 0.084%

    No Known Activations