© 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. 27221
    Prev
    Next
    INDEX
    Explanations

    musical composition and notation

    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
    çģŃ
    -0.10
    æıĸ
    -0.09
    atile
    -0.09
    åĢŁæѤ
    -0.09
    èħIJ
    -0.09
    cano
    -0.09
    ứt
    -0.09
    igy
    -0.09
    åĤij
    -0.09
    acades
    -0.08
    POSITIVE LOGITS
    çļĦæ°Ķæģ¯
    0.11
    家
    0.09
    åĶ±
    0.08
    æ³Ĭ
    0.08
    chant
    0.08
    5
    0.08
    ä¹ŀ
    0.08
    çĻ¾å®¶
    0.08
     worrying
    0.08
    æ¡Ĥ
    0.08
    Activations Density 0.054%

    No Known Activations