© 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. 34447
    Prev
    Next
    INDEX
    Explanations

    emoticons and interjections

    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¯IJ
    -0.10
    ivor
    -0.10
    åıŁ
    -0.09
    addons
    -0.09
    åĽ¿
    -0.08
    èµİ
    -0.08
     Beck
    -0.08
    ä¾ĭå¤ĸ
    -0.08
    èĬ¬
    -0.08
    ìļķ
    -0.08
    POSITIVE LOGITS
    å¥ī
    0.10
    æĮĩçĿĢ
    0.09
    æµĵ
    0.09
    pard
    0.09
    ys
    0.08
     underst
    0.08
    icl
    0.08
    enza
    0.08
     Merkel
    0.08
    è±
    0.08
    Activations Density 0.079%

    No Known Activations