© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    last word or final

    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
    æĶ¯æŁ±
    -0.10
    è¡«
    -0.10
    avig
    -0.09
    çŃ¹å¤ĩ
    -0.09
    çĥ¨
    -0.09
    æŃ¥è¡Į
    -0.09
    à¸Ĺรà¸ĩ
    -0.09
    åıªæĺ¯ä¸ºäºĨ
    -0.08
    åİŁæ²¹
    -0.08
    åīįæıIJæĺ¯
    -0.08
    POSITIVE LOGITS
     final
    0.13
    æĿĥå¨ģ
    0.10
    final
    0.10
    Final
    0.10
    -final
    0.10
    ç»Īæŀģ
    0.10
     Final
    0.09
    å½»åºķ
    0.09
    è£ģå®ļ
    0.09
     FINAL
    0.09
    Activations Density 0.046%

    No Known Activations