© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20656
    Prev
    Next
    INDEX
    Explanations

    causes or results

    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
    à¥į
    -0.09
     sunday
    -0.09
    urent
    -0.08
    åĶ¿
    -0.08
    ä¸ĢæŃ¥
    -0.08
    Ñīен
    -0.08
     neuronal
    -0.08
    ç¬ijçĿĢ说
    -0.08
    æ¼Ķåıĺ
    -0.08
    acci
    -0.08
    POSITIVE LOGITS
    äºĨ好
    0.10
    继
    0.09
    åĩºåİĤ
    0.09
    .setFocus
    0.09
     omn
    0.09
    äºĨåĩł
    0.09
    è¹Ħ
    0.08
    igue
    0.08
    ä»Ģä¹Īåij¢
    0.08
    /extensions
    0.08
    Activations Density 0.675%

    No Known Activations