© 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. 31657
    Prev
    Next
    INDEX
    Explanations

    evidence-based

    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
    arse
    -0.09
    ä¼°åĢ¼
    -0.08
    æ¯ĶèµĽä¸Ń
    -0.08
    åĮ¡
    -0.08
    èĭ¥å¹²
    -0.08
    cour
    -0.08
    dsn
    -0.08
    æķ¦
    -0.08
    obel
    -0.08
     tender
    -0.08
    POSITIVE LOGITS
    æİĪ
    0.10
    å·´æĭī
    0.09
    称åij¼
    0.09
    è¿ĻéĩĮæĺ¯
    0.09
    æĮĩæĮ¥éĥ¨
    0.09
    åĨħè¡£
    0.09
    ä¸į平衡
    0.08
    踩
    0.08
    é»Ķ
    0.08
    uite
    0.08
    Activations Density 0.050%

    No Known Activations