© 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. 27575
    Prev
    Next
    INDEX
    Explanations

    singer, vocalist, vocals

    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
     Music
    -0.10
    éŁ³ä¹IJä¼ļ
    -0.10
     music
    -0.10
    éŁ³ä¹IJ
    -0.10
    秩
    -0.09
    ologne
    -0.09
    尾巴
    -0.09
     MUSIC
    -0.09
    ç°¸
    -0.09
    ستاÙĨ
    -0.09
    POSITIVE LOGITS
     vocals
    0.11
    åij¼åĴĮ
    0.09
    åĹĵ
    0.09
    伤亡
    0.09
    åĶ±
    0.09
    åı£è¯Ń
    0.09
     Bra
    0.09
     Siri
    0.08
    zend
    0.08
    åĸĬ
    0.08
    Activations Density 0.065%

    No Known Activations