© 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. 5610
    Prev
    Next
    INDEX
    Explanations

    football clubs and programming libraries

    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
    tod
    -0.09
    éĿłè°±
    -0.09
    actus
    -0.09
    楣
    -0.09
    toc
    -0.08
    éŃĤ
    -0.08
    åĬª
    -0.08
    esco
    -0.08
     Jad
    -0.08
    leans
    -0.08
    POSITIVE LOGITS
    å´©
    0.09
    æ·¹
    0.09
    æ²īéĩį
    0.09
    ä¸ĸçķĮè§Ĥ
    0.09
    ibile
    0.09
    uing
    0.09
    /he
    0.09
    åĨįéĢł
    0.08
    gent
    0.08
    éģµ
    0.08
    Activations Density 0.002%

    No Known Activations