© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23246
    Prev
    Next
    INDEX
    Explanations

    questions starting with modal verbs

    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
    并ä¸įæĺ¯
    -0.10
    antal
    -0.09
     ÙĦÙĬس
    -0.09
    并éĿŀ
    -0.09
    ä¸į论æĺ¯
    -0.08
    ä¸ĥåħ«
    -0.08
    åĵģçīĮçļĦ
    -0.08
    brands
    -0.08
    å°º
    -0.08
    çĽ²
    -0.08
    POSITIVE LOGITS
     REALLY
    0.12
    羣çļĦ
    0.12
    ä¸İåIJ¦
    0.11
    æĪij羣çļĦ
    0.11
    æīĵå¾Ĺ
    0.10
    éĹ®éĹ®
    0.10
    entic
    0.10
     realmente
    0.09
    æľī没æľī
    0.09
    åĪ°æŶåĢĻ
    0.09
    Activations Density 0.128%

    No Known Activations