© 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. 3680
    Prev
    Next
    INDEX
    Explanations

    costs

    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
    å·¨åŀĭ
    -0.09
    å¾Ī强
    -0.08
    1
    -0.08
    _critical
    -0.07
    0
    -0.07
    æķ¢äºİ
    -0.07
    -turned
    -0.07
    ought
    -0.07
     tiny
    -0.07
    gar
    -0.07
    POSITIVE LOGITS
    åħįéĻ¤
    0.11
    imson
    0.09
     ÑģÑĤоимоÑģÑĤÑĮ
    0.09
    çİĭæľĿ
    0.09
     ÑģÑĤоимоÑģÑĤи
    0.09
    charged
    0.09
    íķĺìĭ¤
    0.09
    iciente
    0.09
    è¿Īè¿Ľ
    0.09
    åİĺ
    0.09
    Activations Density 0.054%

    No Known Activations