© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16887
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    ä¼ļç»Ļ
    -0.11
    åı¯ä»¥è¯´
    -0.11
    ä¼ļ让
    -0.10
    åĩºçİ°äºĨ
    -0.10
    ç»ĻäºĪäºĨ
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    åı¯ä»¥è®©
    -0.10
    èĥ½è®©
    -0.10
    ä»ĸå·²ç»ı
    -0.10
    ä¸įæĢķ
    -0.10
    POSITIVE LOGITS
    åģļçļĦäºĭæĥħ
    0.13
    åģļçļĦäºĭ
    0.12
    åıijæĮ¥ä½ľçĶ¨
    0.12
     zien
    0.11
    çľĭåĩº
    0.10
    åĸĺ
    0.10
    æĦŁåıĹåĪ°
    0.10
    åģļä»Ģä¹Ī
    0.09
    产çĶŁ
    0.09
    èĩªçĶ±
    0.09
    Activations Density 0.015%

    No Known Activations