© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37776
    Prev
    Next
    INDEX
    Explanations

    Modal verbs and necessity/desire

    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
    æľ¬è½®
    -0.09
    çļĦéĢīæĭ©
    -0.09
    åĽº
    -0.08
     heard
    -0.08
    èĨı
    -0.08
     consensus
    -0.08
    çIJĨäºĭéķ¿
    -0.08
    åĴ½
    -0.08
    åķĨä¼ļ
    -0.08
    éľĢè¦ģ注æĦı
    -0.08
    POSITIVE LOGITS
    çŁ¥å·±
    0.13
    éĢıæĺİ
    0.12
    çĽijæµĭ
    0.12
    çĽijæݧ
    0.12
    çŁ¥éģĵèĩªå·±
    0.12
     information
    0.11
    精确
    0.11
     ìłķë³´
    0.11
    æĥ³çŁ¥éģĵ
    0.11
    æİĮæı¡
    0.11
    Activations Density 0.353%

    No Known Activations