© 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. 38837
    Prev
    Next
    INDEX
    Explanations

    with or to followed by a word

    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
    IC
    -0.10
    icus
    -0.10
    å¾ģæ±Ĥ
    -0.09
    uze
    -0.09
    æĤ²
    -0.09
    annis
    -0.09
    acl
    -0.08
    京
    -0.08
    份
    -0.08
    鸳
    -0.08
    POSITIVE LOGITS
    å½¼æѤ
    0.15
    åIJĦèĩªçļĦ
    0.11
    åIJĦèĩª
    0.11
    ä¸ŃåİŁ
    0.10
    åľ¨ä¸Ģèµ·
    0.10
    ä¹ĭéĹ´çļĦ
    0.10
     ìĦľë¡ľ
    0.10
    cret
    0.10
    ä¹ĭéĹ´
    0.10
    çħ¨
    0.09
    Activations Density 0.348%

    No Known Activations