© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52511
    Prev
    Next
    INDEX
    Explanations

    video recording quality

    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
    æݨéĢģ
    -0.10
    ç¬ı
    -0.09
    .Persistent
    -0.09
    交ç»Ļ
    -0.09
    åĨįä¹Łæ²¡æľī
    -0.09
    æģIJ
    -0.09
    åijĵ
    -0.09
    -prepend
    -0.09
    è¿Ļæĺ¯æĪij们
    -0.09
    lian
    -0.09
    POSITIVE LOGITS
    æħ¢
    0.14
     slow
    0.13
    Slow
    0.11
    é«ĺéĢŁ
    0.11
     Slow
    0.11
     slows
    0.10
    slow
    0.10
     slowed
    0.10
     slower
    0.09
    å¿«
    0.09
    Activations Density 0.053%

    No Known Activations