© 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. 33101
    Prev
    Next
    INDEX
    Explanations

    First reasons or starters

    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
    anol
    -0.10
    æĪijä»¬ä¹Ł
    -0.10
    åı¦ä¸Ģ
    -0.10
    èĥ½è¾¾åĪ°
    -0.10
    åħ¶ä»ĸ
    -0.09
    ä½łä¹Ł
    -0.09
    åĬ¼
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    æĿ¯åŃIJ
    -0.08
    ä¹Łè¢«
    -0.08
    POSITIVE LOGITS
    é¦ĸåħĪæĺ¯
    0.10
    å®ıè§Ĥ
    0.10
    é¦ĸåħĪ
    0.10
    _RS
    0.09
    æĺ¯å¯¹
    0.09
    æĢģ度
    0.08
    å¥ijåIJĪ
    0.08
    ä½ĵçİ°åľ¨
    0.08
    SED
    0.08
    ToEnd
    0.08
    Activations Density 0.117%

    No Known Activations