© 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. 53978
    Prev
    Next
    INDEX
    Explanations

    describing or description

    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
    åѦéĹ®
    -0.10
    è¿Ľä¿®
    -0.09
    æ®ī
    -0.08
    çīĩåŃIJ
    -0.08
    ä»
    -0.08
    â½°
    -0.08
     воп
    -0.08
     ther
    -0.08
     prog
    -0.08
    æľªæĪIJå¹´
    -0.08
    POSITIVE LOGITS
    æııè¿°
    0.27
     description
    0.20
    æııåĨĻ
    0.20
     descriptions
    0.19
     describe
    0.18
    æııç»ĺ
    0.18
     опиÑģание
    0.18
     describing
    0.17
    description
    0.17
    (description
    0.17
    Activations Density 0.084%

    No Known Activations