© 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. 56227
    Prev
    Next
    INDEX
    Explanations

    Ravens, Seahawks, Bengals, Baltimore

    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
    å¹³åĩ¡
    -0.09
     ÑħоÑĤÑı
    -0.09
    æ¯ĴæĢ§
    -0.09
    ç´Ĭä¹±
    -0.09
    berman
    -0.09
    çİ©æĦı
    -0.09
    æĻ®æŁ¥
    -0.08
    obo
    -0.08
    -ie
    -0.08
    代表大ä¼ļ
    -0.08
    POSITIVE LOGITS
    coat
    0.09
    mind
    0.09
    è´¨åľ°
    0.09
    绽
    0.08
    ending
    0.08
    inning
    0.08
    воÑĢ
    0.08
    çķĮçļĦ
    0.08
    åĺŁ
    0.08
    beh
    0.08
    Activations Density 0.003%

    No Known Activations