© 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. 10917
    Prev
    Next
    INDEX
    Explanations

    hit songs and albums

    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
    èµ°ä¸ĭåİ»
    -0.12
    å°Ĭ严
    -0.09
    æijĦ
    -0.09
    æľ¬æľŁ
    -0.09
    .timedelta
    -0.09
    碴
    -0.09
    缴éĢļ车
    -0.09
    æĶĿ
    -0.09
    马æĭīæĿ¾
    -0.09
    æľīæĦı
    -0.08
    POSITIVE LOGITS
    çķħéĶĢ
    0.14
    çĪĨ款
    0.13
    ä¹ĭä½ľ
    0.11
    æµģè¡Į
    0.11
    -hit
    0.10
     hit
    0.10
     hits
    0.10
    æµģè¡ĮçļĦ
    0.10
     success
    0.10
     blockbuster
    0.10
    Activations Density 0.105%

    No Known Activations