© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    still, remain, relevant, today, later

    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
    夷
    -0.09
    æĭħ
    -0.09
    å±Ĥå±Ĥ
    -0.09
    ä½Ĩä¸įéĻIJ
    -0.09
    och
    -0.09
    æ¦Ħ
    -0.09
    红è±Ĩ
    -0.08
     Lund
    -0.08
    æ·ŀ
    -0.08
     further
    -0.08
    POSITIVE LOGITS
    ä¾ĿçĦ¶
    0.16
    ä»įçĦ¶
    0.16
    ä»įçĦ¶æĺ¯
    0.15
    ä¾ĿçĦ¶æĺ¯
    0.15
    ä¾Ŀæŧ
    0.13
    ä»įæĺ¯
    0.11
    ä»įæľī
    0.11
    ä¾Ŀæŧæĺ¯
    0.11
    ä¿Ŀé²ľ
    0.11
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.11
    Activations Density 0.072%

    No Known Activations