© 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. 26729
    Prev
    Next
    INDEX
    Explanations

    accidental actions

    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
    quez
    -0.11
    ç¼µ
    -0.10
    åģİ
    -0.10
    åĵº
    -0.10
    æİıåĩº
    -0.09
    åŃĺåľ¨éĹ®é¢ĺ
    -0.09
    åĭ
    -0.09
    combe
    -0.09
     поÑģл
    -0.09
    irectory
    -0.09
    POSITIVE LOGITS
    ä¸įå°ıå¿ĥ
    0.21
    åģ¶çĦ¶
    0.20
     accidental
    0.19
    æĦıå¤ĸ
    0.18
    æĹłæĦı
    0.17
    ä¸įç»ıæĦı
    0.17
    误
    0.16
     accidentally
    0.16
    å·§åIJĪ
    0.15
     accident
    0.14
    Activations Density 0.101%

    No Known Activations