© 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. 18238
    Prev
    Next
    INDEX
    Explanations

    JSON delimiters or structured data

    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
     =========================================================================
    -0.09
    çĦ¶æĺ¯
    -0.09
     HAPP
    -0.09
    bolt
    -0.09
    人éĥ½
    -0.09
    ä¹Łä¸įæĺ¯
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    ello
    -0.08
    å¤ł
    -0.08
    å¨ħ
    -0.08
    POSITIVE LOGITS
    syn
    0.10
    ä¸Ģç«Ļ
    0.09
    side
    0.09
    sy
    0.08
    ensity
    0.08
    ä¸Ģå®ļ
    0.08
    suite
    0.08
     Tình
    0.08
    ä¸Ģå®ļæĺ¯
    0.08
    amoto
    0.08
    Activations Density 0.060%

    No Known Activations