© 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. 32549
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
    åħ¨åijĺ
    -0.09
    èĽĨ
    -0.09
    åĮ¯
    -0.09
    è´±
    -0.09
    åħ¨æĸ°çļĦ
    -0.09
    åħ¨åľº
    -0.09
    autoload
    -0.08
    åħ¨æĸ°
    -0.08
    iska
    -0.08
    mmo
    -0.08
    POSITIVE LOGITS
    å¢ĥ
    0.11
    å¥
    0.09
    æ²ĵ
    0.09
    -env
    0.09
    .ua
    0.09
    xab
    0.09
    宽
    0.08
    éºŁ
    0.08
    åı¯ä»¥çĽ´æİ¥
    0.08
    ä½łå°±
    0.08
    Activations Density 0.026%

    No Known Activations