© 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. 35478
    Prev
    Next
    INDEX
    Explanations

    preposition 'in' or 'into'

    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
    å½ĵæŶçļĦ
    -0.09
    æīĢåľ¨
    -0.09
    _completion
    -0.09
    ç»ıæµİæĬĢæľ¯
    -0.09
    è§Ī
    -0.09
     rus
    -0.08
    éļ¾å¾Ĺ
    -0.08
    è¦ģçľĭ
    -0.08
    å½¼
    -0.08
     Restr
    -0.08
    POSITIVE LOGITS
    éĽĨè£ħç®±
    0.09
    DLL
    0.09
    è¯ļ
    0.09
    ark
    0.09
    æįŀ
    0.09
    ç¬ĥ
    0.08
    ðŁijĨ
    0.08
     htt
    0.08
    éĿł
    0.08
    åı®
    0.08
    Activations Density 0.023%

    No Known Activations