© 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. 11647
    Prev
    Next
    INDEX
    Explanations

    years ago, I, it, we

    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
    åİŁæĸĩåľ°åĿĢ
    -0.12
    åĽłä¸ºä»ĸ们
    -0.11
    äºİæĺ¯æĪij
    -0.11
    ãģĿãģ®ä»ĸ
    -0.11
    ä½Ĩä»ĸ们
    -0.11
    éļıåIJİ
    -0.11
     기íĥĢ
    -0.10
    åŃĻåŃIJ
    -0.10
    åľ¨å½ĵåľ°
    -0.10
    èĢĮåľ¨
    -0.10
    POSITIVE LOGITS
    æĪij们
    0.08
     we
    0.08
    ä¹Łå°±æĺ¯
    0.08
    å®ĥ
    0.08
    hin
    0.08
    msp
    0.07
    æĪij们ä¼ļ
    0.07
    cretion
    0.07
    ded
    0.07
    åīĩ
    0.07
    Activations Density 0.224%

    No Known Activations