© 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. 6828
    Prev
    Next
    INDEX
    Explanations

    foster, nurture, cultivate

    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
    ton
    -0.09
    ENDED
    -0.09
    бег
    -0.08
    åĮĨåĮĨ
    -0.08
    doors
    -0.08
    çªģçł´åı£
    -0.08
    ation
    -0.08
    æī°ä¹±
    -0.08
    ourses
    -0.08
    LEAR
    -0.08
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.10
    åIJĪä½ľåħ³ç³»
    0.09
     hè
    0.09
    议论
    0.09
    ë§ģ
    0.09
    ÑĥлÑĮ
    0.09
    ä¸ĢèĤ¡
    0.09
    èĵ¼
    0.09
    /operator
    0.08
    urning
    0.08
    Activations Density 0.005%

    No Known Activations