© 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. 29701
    Prev
    Next
    INDEX
    Explanations

    macbook pros and notebooks

    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
    ingo
    -0.10
    æī¯
    -0.09
    zsche
    -0.09
    个åĪ«
    -0.08
    è´¯
    -0.08
    å®ŀåľ¨
    -0.08
    æİĸ
    -0.08
    ç§ī
    -0.08
    ç´«
    -0.08
     Hop
    -0.08
    POSITIVE LOGITS
    ç¬Ķè®°æľ¬
    0.12
    åIJįæł¡
    0.11
     notebooks
    0.10
     notebook
    0.10
    .notes
    0.10
    æĹħ
    0.09
    Odd
    0.09
    odd
    0.09
     Ramos
    0.09
     Overnight
    0.09
    Activations Density 0.177%

    No Known Activations