© 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. 56314
    Prev
    Next
    INDEX
    Explanations

    either raw or forms

    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
    voy
    -0.11
     voy
    -0.08
     Handy
    -0.08
    åIJ»
    -0.08
    èįī
    -0.08
     ÑĢанее
    -0.08
     ingredients
    -0.07
    essen
    -0.07
     traffic
    -0.07
     Ingredients
    -0.07
    POSITIVE LOGITS
    å¤ļç§įå½¢å¼ı
    0.15
    æ·±åĬłå·¥
    0.13
    ä»»ä½ķå½¢å¼ı
    0.12
    ä¸İåħ¶ä»ĸ
    0.11
    çļĦåĬŀæ³ķ
    0.11
    à¸Ļำà¹Ħà¸Ľ
    0.11
    å°Ĩåħ¶
    0.11
    åĩī
    0.10
    åĬłå·¥
    0.10
    å®ĥåı¯ä»¥
    0.10
    Activations Density 0.056%

    No Known Activations