© 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. 40251
    Prev
    Next
    INDEX
    Explanations

    caffeine and nicotine

    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
    .Microsoft
    -0.10
    ä¸ŃåĽ½å¸Ĥåľº
    -0.10
    ëĭµ
    -0.09
    \xd
    -0.09
    éĺ²èĮĥ
    -0.09
    ä¸įåĥı
    -0.09
    _Variable
    -0.09
    esModule
    -0.09
    å®ŀä¹ł
    -0.09
    æĪij们ä¸Ģèµ·
    -0.09
    POSITIVE LOGITS
    acy
    0.09
     Others
    0.08
    è¶ħæłĩ
    0.08
    æĺĶ
    0.08
    æ·±åĪ»
    0.08
     Pill
    0.08
     Apt
    0.08
    lic
    0.08
    agher
    0.07
    æ·±åİļ
    0.07
    Activations Density 0.012%

    No Known Activations