© 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. 38431
    Prev
    Next
    INDEX
    Explanations

    song lyrics

    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
    â¿
    -0.10
     Bris
    -0.09
    浩
    -0.09
    ä¸Ńä»ĭ
    -0.09
    禧
    -0.09
    /qt
    -0.09
    å°ıåºĹ
    -0.09
    åŁºæľ¬åİŁåĪĻ
    -0.09
    æķ´é¡¿
    -0.08
    ç´ł
    -0.08
    POSITIVE LOGITS
    æŃĮè¯į
    0.16
     lyrics
    0.10
    è©ŀ
    0.10
    æŃĮæĽ²
    0.10
     вок
    0.10
    è¯ĹæŃĮ
    0.09
    è¯Ĺè¯į
    0.09
    è¯į
    0.09
     poem
    0.09
     пеÑģ
    0.09
    Activations Density 0.142%

    No Known Activations