© 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. 50099
    Prev
    Next
    INDEX
    Explanations

    football clubs and competitions

    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
    ä½ľåĵģ
    -0.10
    åıijå±ķè§ĦåĪĴ
    -0.10
    DR
    -0.09
    åİļ
    -0.09
     dol
    -0.09
    ä¼łéĢĴ
    -0.08
    _DR
    -0.08
    忽çĦ¶
    -0.08
     Drum
    -0.08
    éĢļè¡Įè¯ģ
    -0.08
    POSITIVE LOGITS
    ä¸Ńæĸ°
    0.12
    è¿Ļæł·ä¸Ģ
    0.09
    ç²±
    0.09
    åĮĹ京æŶéĹ´
    0.09
     Valk
    0.09
    ä¸Ģç«Ļ
    0.08
    èĮ´
    0.08
    argon
    0.08
    ÙĪار
    0.08
    è°ļ
    0.08
    Activations Density 0.188%

    No Known Activations