© 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. 57964
    Prev
    Next
    INDEX
    Explanations

    voice actress, actor, voice, speech, audio

    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
    èĥĢ
    -0.09
    ç»ıèIJ¥
    -0.09
    å¼ŁåħĦ
    -0.09
    娣
    -0.08
    ç»ıèIJ¥æ¨¡å¼ı
    -0.08
    thur
    -0.08
    èĪŀè¹Ī
    -0.08
     Plane
    -0.08
    è¿«
    -0.08
    à¹ĭ
    -0.08
    POSITIVE LOGITS
    è¯ŃéŁ³
    0.16
     voice
    0.14
    éħįéŁ³
    0.13
    æľĹ
    0.13
    å£°éŁ³
    0.13
    Voice
    0.13
    åıijéŁ³
    0.13
     Voice
    0.12
    声
    0.12
     giá»įng
    0.12
    Activations Density 0.077%

    No Known Activations