© 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. 35085
    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
    åIJĮå¿Ĺ
    -0.09
    oreach
    -0.09
    åIJĦæĸ¹éĿ¢
    -0.08
    ovel
    -0.08
    æľīæĽ´å¤ļçļĦ
    -0.08
     met
    -0.08
    åīij
    -0.08
    åŁİéķĩåĮĸ
    -0.08
    çĢij
    -0.08
     shut
    -0.07
    POSITIVE LOGITS
     happened
    0.12
     happ
    0.12
    åıijçĶŁåľ¨
    0.11
     Ñģобой
    0.10
    åħ·ä½ĵåĨħ容
    0.10
    迹象
    0.09
     happen
    0.09
    nel
    0.09
     знак
    0.09
     happens
    0.09
    Activations Density 0.031%

    No Known Activations