© 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. 47677
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by consequences

    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
     Rosenstein
    -0.10
     Sunder
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    è¡Įä¸ļä¸Ń
    -0.09
    èļ¬
    -0.09
    就被
    -0.08
     teas
    -0.08
    ðŁĴ¢
    -0.08
    没æľīæĥ³åĪ°
    -0.08
    ä¸įåĨįæĺ¯
    -0.08
    POSITIVE LOGITS
    导èĩ´
    0.16
    使
    0.15
    使å¾Ĺ
    0.15
    带æĿ¥
    0.13
    å°İèĩ´
    0.13
    使æĪij
    0.12
    迫使
    0.12
    åħģ许
    0.11
    å¼ķæĿ¥
    0.11
    ä¿ĥ使
    0.10
    Activations Density 0.327%

    No Known Activations