© 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. 31066
    Prev
    Next
    INDEX
    Explanations

    could have + past participle

    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
    å¢ŀè¿Ľ
    -0.10
    è°Ħ
    -0.10
    æĮij
    -0.09
    rael
    -0.09
     enrich
    -0.09
    ç¿ħ
    -0.09
    诱
    -0.09
    ãģľ
    -0.09
    leton
    -0.08
    ä½łçİ°åľ¨
    -0.08
    POSITIVE LOGITS
    oyo
    0.09
    abric
    0.08
    ç¼
    0.08
    ç«ij
    0.08
    iminary
    0.08
    èĨº
    0.08
     feather
    0.08
    orda
    0.08
    ç¥ŀæĥħ
    0.08
    åģľçķĻåľ¨
    0.08
    Activations Density 0.015%

    No Known Activations