© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    below the X

    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
    fully
    -0.10
    emble
    -0.09
    illos
    -0.09
    ä¹Łå°±æĺ¯è¯´
    -0.09
    ually
    -0.09
    YST
    -0.09
    ifice
    -0.09
    imeo
    -0.09
    iendo
    -0.09
    owanie
    -0.09
    POSITIVE LOGITS
    neath
    0.11
    ance
    0.10
    æĽ´ä½İ
    0.10
    ç§įç§į
    0.09
    éĤ£ç§į
    0.09
    ground
    0.09
    ãģĴãĤĭ
    0.09
    cej
    0.09
    å»ī
    0.09
    icz
    0.09
    Activations Density 0.054%

    No Known Activations