© 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. 19891
    Prev
    Next
    INDEX
    Explanations

    song or songs

    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
    ç»ŀ
    -0.09
    ç§ī
    -0.09
    orts
    -0.09
    路段
    -0.09
    .constructor
    -0.09
    Kin
    -0.09
    auc
    -0.09
     LOT
    -0.09
    妹
    -0.08
    immer
    -0.08
    POSITIVE LOGITS
    å¿®
    0.10
    endar
    0.09
    åĪ©åĻ¨
    0.09
    stress
    0.08
    lets
    0.08
    .ends
    0.08
    nect
    0.08
    èĴ¿
    0.08
     Vogue
    0.08
    ä¼ģ
    0.08
    Activations Density 0.028%

    No Known Activations