© 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. 47724
    Prev
    Next
    INDEX
    Explanations

    romantic contexts

    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°º
    -0.09
    l
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    _SR
    -0.08
    ivor
    -0.08
    éĥ¨åĪĨ
    -0.08
     Sandbox
    -0.08
    åīĸ
    -0.07
    æĸ¤
    -0.07
    å¼¥
    -0.07
    POSITIVE LOGITS
    allee
    0.13
    ä¹ĭæĹħ
    0.11
    íĮĶ
    0.11
    åľºéĿ¢
    0.11
    èĻŀ
    0.10
    emarks
    0.10
    ibraries
    0.10
     ÑĢоман
    0.10
     lã
    0.09
    strup
    0.09
    Activations Density 0.003%

    No Known Activations