© 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. 58349
    Prev
    Next
    INDEX
    Explanations

    integrated

    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
    /dr
    -0.10
    æŶåĢĻ
    -0.09
     Jensen
    -0.09
    çĦĺ
    -0.09
    çĶ¨éĩı
    -0.09
    åĪĨæīĭ
    -0.08
    uyá»ģn
    -0.08
    евиÑĩ
    -0.08
    RELATED
    -0.08
    овиÑĩ
    -0.08
    POSITIVE LOGITS
    èĢĮåıĪ
    0.11
     approached
    0.10
    ness
    0.10
    äºĨ许å¤ļ
    0.09
    å°±è¿ij
    0.09
    é¹ij
    0.09
    大家ä¸Ģèµ·
    0.09
     impro
    0.09
    ordinated
    0.09
    èĤ²äºº
    0.09
    Activations Density 0.034%

    No Known Activations