© 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. 55647
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
    9
    -0.09
    约åIJĪ
    -0.09
     equivalents
    -0.08
    ars
    -0.08
    缸å½ĵäºİ
    -0.08
    ç«Ń
    -0.08
     Cher
    -0.08
    arf
    -0.08
    7
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    æľīæŶåĢĻ
    0.11
    _px
    0.10
    èĹIJ
    0.10
    ä¸įåı¯éģ¿åħį
    0.10
    ä¹Łè¢«
    0.10
    çĶ¸
    0.10
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.10
    ä¼ļ被
    0.10
    漪
    0.09
    åı£å¤´
    0.09
    Activations Density 0.134%

    No Known Activations