© 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. 53605
    Prev
    Next
    INDEX
    Explanations

    music sales and downloads

    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
    éģ¥
    -0.11
    çĶ¨éĩı
    -0.10
    æĥľ
    -0.10
    _IMPL
    -0.09
    raising
    -0.09
    пÑĢоÑģ
    -0.09
    æī¿æİ¥
    -0.09
    ино
    -0.09
    åijĬ
    -0.09
    oom
    -0.09
    POSITIVE LOGITS
     music
    0.11
    éŁ³ä¹IJ
    0.11
    music
    0.10
     iTunes
    0.09
    åĨ²
    0.09
    åĭ¾
    0.09
    éŁ³æ¨Ĥ
    0.08
    èĹı
    0.08
    山路
    0.08
    çŀ¥
    0.08
    Activations Density 0.194%

    No Known Activations