© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings after punctuation

    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
    åĪĩ
    -0.09
    ëįĶëĿ¼
    -0.09
    åIJ¯ç¤º
    -0.09
    æļĿ
    -0.09
    è¿·æĥij
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    برا
    -0.08
    åħ±èµ¢
    -0.08
    âĸĮ
    -0.08
    oine
    -0.08
    POSITIVE LOGITS
    odia
    0.09
    游泳
    0.09
    é»ĺé»ĺåľ°
    0.08
    ç§ijåѦæĬĢæľ¯
    0.08
     clo
    0.08
    AME
    0.08
     Alg
    0.08
    å°Ĩè¿İæĿ¥
    0.07
     Jennings
    0.07
    UIS
    0.07
    Activations Density 0.089%

    No Known Activations