© 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. 31159
    Prev
    Next
    INDEX
    Explanations

    music classification

    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
    缴è¾ĸ
    -0.10
    ä¸ĺ
    -0.09
    èĭįçĻ½
    -0.09
    anged
    -0.09
    è§Ĥå½±
    -0.09
    å¢ŀèµĦ
    -0.08
    åī§åľº
    -0.08
    iant
    -0.08
    iais
    -0.08
    å¤ĸèµĦ
    -0.08
    POSITIVE LOGITS
    ä¸įå¾Ĺ
    0.09
    è¿Ļ对äºİ
    0.09
    aro
    0.09
    _opcode
    0.09
     воÑĤ
    0.09
    羡
    0.09
     kull
    0.08
    é¾Ļ头
    0.08
    çªģåıij
    0.08
    _PRO
    0.08
    Activations Density 0.069%

    No Known Activations