© 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. 54522
    Prev
    Next
    INDEX
    Explanations

    criticism of, expressing views, arguing that

    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
    åĨ³å®ļäºĨ
    -0.09
    åıij表äºĨ
    -0.09
    è¦ģä¹Ī
    -0.09
    侥幸
    -0.09
    è°®
    -0.09
     Ñħа
    -0.08
    ä¸Ģ缴å¤Ħäºİ
    -0.08
    ä½ľå¼Ĭ
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    骡
    -0.08
    POSITIVE LOGITS
    éĢĤå½ĵçļĦ
    0.12
    éĢĤ度
    0.11
    åģ¶å°Ķ
    0.11
    ä¸Ģå®ļç¨ĭ度
    0.11
    éļ¾åħį
    0.11
    åŃĺåľ¨ä¸Ģå®ļ
    0.10
    éļ¾éģĵ
    0.10
    ä¸įåı¯éģ¿åħį
    0.10
    å¿ħè¦ģçļĦ
    0.10
    åIJĪçIJĨçļĦ
    0.10
    Activations Density 0.238%

    No Known Activations