© 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. 11305
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating future or possibility

    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
    ned
    -0.09
    羡
    -0.09
    æĬļæij¸
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.08
    大åıij
    -0.08
    åºĶ该æĢİä¹Ī
    -0.08
    ä¼ĹæīĢ
    -0.08
    认å®ļ
    -0.08
     sou
    -0.08
    bens
    -0.08
    POSITIVE LOGITS
    _stderr
    0.10
    _HOT
    0.09
    пÑĢе
    0.09
    æĤ²åī§
    0.09
    æľīèĥ½åĬĽ
    0.09
     Armen
    0.09
    ÙĦØŃ
    0.08
    widgets
    0.08
    ç»¿åľ°
    0.08
    erva
    0.08
    Activations Density 0.251%

    No Known Activations