© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 6658
    Prev
    Next
    INDEX
    Explanations

    points, goals, assists, TDs, starts

    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
    æľīäºĨ
    -0.10
    ä¹Łåıªèĥ½
    -0.10
    èĭ¥å¹²
    -0.09
    å·¥ä¸ļä¼ģä¸ļ
    -0.09
    åıijå±ķçļĦ
    -0.09
    ä¹Łè®©
    -0.09
    æĪ´ä¸Ĭ
    -0.09
     chÃŃ
    -0.09
    æĦŁæŁĵèĢħ
    -0.09
    ãĤ
    -0.09
    POSITIVE LOGITS
    isia
    0.10
    æĥĬ人
    0.09
    éĤ£ç§į
    0.09
    สà¸Ķ
    0.08
    åŁĻ
    0.08
    é«ĺä½į
    0.08
    _FE
    0.08
    ÙħصÙĦ
    0.08
    é²ľæĺİ
    0.08
    踩
    0.08
    Activations Density 0.037%

    No Known Activations