© 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. 32602
    Prev
    Next
    INDEX
    Explanations

    Football abbreviations

    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
    åĭ¢
    -0.09
    ä¸ĩäºĭ
    -0.09
    _Format
    -0.09
    åĬ¿
    -0.09
    uit
    -0.08
     Ud
    -0.08
    åħľ
    -0.08
    åIJĦæľī
    -0.08
    ä»Ģ
    -0.08
    ç¿ĺ
    -0.08
    POSITIVE LOGITS
    å®īåħ¨äºĭæķħ
    0.12
    çĤĬ
    0.10
    è½»
    0.09
    äºĭæķħ
    0.09
     controversial
    0.09
    ลà¸ļ
    0.09
    äºīè®®
    0.09
    é£İéĻ©
    0.09
    ìĦ±ìĿ´
    0.09
    ooter
    0.09
    Activations Density 0.208%

    No Known Activations