© 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. 11380
    Prev
    Next
    INDEX
    Explanations

    solo piano and concertos

    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
    å¹³æķ´
    -0.10
    èµĬ
    -0.09
    åłĤ
    -0.09
    çĨĻ
    -0.09
    odom
    -0.09
    åħĥå®Ŀ
    -0.08
    ç©·
    -0.08
    å¼ķæĵİ
    -0.08
    ме
    -0.08
    pack
    -0.08
    POSITIVE LOGITS
    寤
    0.10
    çĭ¬
    0.09
    ÕŃ
    0.09
    夹
    0.08
    é¢Ĩ
    0.08
    maze
    0.08
    NECT
    0.08
    afka
    0.08
    -only
    0.08
     solo
    0.08
    Activations Density 0.040%

    No Known Activations