© 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. 58497
    Prev
    Next
    INDEX
    Explanations

    musical notes and instruments

    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
    æĹĮ
    -0.09
     Maur
    -0.09
    è²ĺ
    -0.09
    éĩijå±±
    -0.08
    æļ´
    -0.08
    缯
    -0.08
     Ron
    -0.08
    åĢ¾æĸľ
    -0.08
    bold
    -0.08
    .Parcel
    -0.08
    POSITIVE LOGITS
    å¥ı
    0.13
    è°±åĨĻ
    0.12
    åħ±æĮ¯
    0.12
    çIJ´
    0.12
    弦
    0.12
     chords
    0.11
    åĴĮè°IJ
    0.11
    notes
    0.10
    note
    0.10
    æĹ¶ç©º
    0.09
    Activations Density 0.047%

    No Known Activations