© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21032
    Prev
    Next
    INDEX
    Explanations

    football season games players

    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
    èİĵ
    -0.10
    hips
    -0.09
    ç±³å°Ķ
    -0.09
    ä¹ĭåĬĽ
    -0.09
    éªĸ
    -0.09
     unf
    -0.09
    flat
    -0.09
    ew
    -0.09
    ings
    -0.09
    åĬŀäºĭ
    -0.09
    POSITIVE LOGITS
    oting
    0.09
    çİĭåŃIJ
    0.09
    town
    0.08
    eras
    0.08
     Alv
    0.08
    æľīäºĨ
    0.08
    stad
    0.08
    shire
    0.08
     hart
    0.08
     Sandwich
    0.08
    Activations Density 0.031%

    No Known Activations