© 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. 53521
    Prev
    Next
    INDEX
    Explanations

    advise to always or never

    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
    åģļçļĦ
    -0.09
    ased
    -0.09
    æŀ¶
    -0.09
    tü
    -0.09
    æĺŁå·´
    -0.09
    æ¯ıæľĪ
    -0.09
    çĽ¼
    -0.09
    æ¯ıåij¨
    -0.08
    çī§åľº
    -0.08
    åĸľ
    -0.08
    POSITIVE LOGITS
    çĭ®
    0.09
    èݲèĬ±
    0.09
    åĴĮåıijå±ķ
    0.08
    ç¼Ļ
    0.08
    ioni
    0.08
    æ¿Ĥ
    0.08
    lian
    0.08
    ä¼´éļıçĿĢ
    0.08
     foll
    0.08
     ALWAYS
    0.08
    Activations Density 0.024%

    No Known Activations