© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47409
    Prev
    Next
    INDEX
    Explanations

    photography, photographer, pictures

    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
    Negative Logits
    æīĴ
    -0.10
     Mare
    -0.09
    æī¶
    -0.09
    è¯Ī
    -0.09
    itone
    -0.09
    侬
    -0.08
    /vnd
    -0.08
    emon
    -0.08
    UCE
    -0.08
    ä¹±
    -0.08
    POSITIVE LOGITS
    å¼łå®¶çķĮ
    0.10
    preci
    0.09
     Gerçek
    0.09
     Workspace
    0.08
    ç¢Ľ
    0.08
    æīĵæĸŃ
    0.08
    otation
    0.08
    é»Ħå±±
    0.08
    _variant
    0.08
    chen
    0.08
    Activations Density 0.082%

    No Known Activations