© 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. 17697
    Prev
    Next
    INDEX
    Explanations

    song by singer-songwriter

    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
    æīĵ好
    -0.11
    èķī
    -0.11
    ivre
    -0.11
    èĮİ
    -0.10
    éħįåIJĪ
    -0.10
    åīįåĪĹèħº
    -0.10
    åľ¨å¤ĸ
    -0.09
    æµģåĬ¨
    -0.09
    èİ
    -0.09
    bate
    -0.09
    POSITIVE LOGITS
     ticket
    0.08
    ç»Ļä½łä»¬
    0.08
    Cro
    0.08
    女çĶŁ
    0.07
    è¹Ļ
    0.07
    mh
    0.07
     cro
    0.07
     Cro
    0.07
     Ferry
    0.07
    åĩºåĽ½çķĻåѦ
    0.07
    Activations Density 0.181%

    No Known Activations