© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    education and academic roles

    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
    afx
    -0.09
     bore
    -0.08
    ооÑĢ
    -0.08
    roz
    -0.08
    endir
    -0.08
    ç§ijåѦåıijå±ķ
    -0.08
    å¥ĸéĩij
    -0.08
    éĢłèĪ¹
    -0.08
    å¢ĥ
    -0.08
    æIJ¬
    -0.08
    POSITIVE LOGITS
    å¸ĪèĮĥ
    0.19
    å¸ĪèĮĥ大åѦ
    0.10
    å¹¼åĦ¿åĽŃ
    0.10
    示èĮĥ
    0.10
    qua
    0.09
    ç¬ı
    0.09
    çĥ¨
    0.09
    ä¸Ńå°ıåѦ
    0.09
    æī¹
    0.09
     Baton
    0.09
    Activations Density 0.047%

    No Known Activations