© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12312
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by article/preposition

    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
    Negative Logits
    -0.10
     ÑĦоÑĢмиÑĢов
    -0.10
     zwar
    -0.09
    affe
    -0.09
    ä¸įä»ħè¦ģ
    -0.08
    è®·
    -0.08
    ä¹ĭä½Ļ
    -0.08
    ÑģпеÑĪ
    -0.08
    ä»ħä¾Ľ
    -0.08
    以èī²
    -0.08
    POSITIVE LOGITS
    å°±è¡ĮäºĨ
    0.20
    å°±åı¯ä»¥äºĨ
    0.19
    åį³åı¯
    0.15
    å°±è¡Į
    0.14
    就好äºĨ
    0.14
    èĢĮå·²
    0.14
    å°±å¤ŁäºĨ
    0.13
    å°±åı¯ä»¥
    0.13
    å°±çŁ¥éģĵ
    0.12
    å°±èĥ½
    0.12
    Activations Density 0.050%

    No Known Activations