© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8881
    Prev
    Next
    INDEX
    Explanations

    guide you, market in, interested in

    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
    otron
    -0.10
    ฯ
    -0.09
    á»ĩm
    -0.09
    ÙĬÙĪ
    -0.08
    olley
    -0.08
    Å¡ÃŃ
    -0.08
    ï¸ı
    -0.08
     Holt
    -0.08
    -ser
    -0.08
    æ·«
    -0.08
    POSITIVE LOGITS
    æĪijèĩªå·±
    0.09
    æŃĨ
    0.09
    æľ¬äºº
    0.09
    éĺĹ
    0.08
     alike
    0.08
    ãģªãģ®ãģł
    0.08
    该æĢİä¹Ī
    0.08
    æīĢè°ĵçļĦ
    0.08
    èĢģ乡
    0.07
    inium
    0.07
    Activations Density 3.475%

    No Known Activations