© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    more about

    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
    ç½ijåıĭè¯Ħ论
    -0.09
    olut
    -0.09
    zb
    -0.09
    çĽ¸å·®
    -0.09
     haunt
    -0.08
    eel
    -0.08
    gross
    -0.08
    è¯ĺ
    -0.08
    ort
    -0.07
    alchemy
    -0.07
    POSITIVE LOGITS
    ä¸įå¤ļ
    0.10
    è¿ĺåı¯
    0.09
    èĺ¸
    0.09
    åģļ个
    0.09
    å±ģ
    0.09
    æĺ¯ä¸Ģ座
    0.09
    积æŀģåıĤä¸İ
    0.09
    _about
    0.09
    LEEP
    0.08
    èµĦ讯
    0.08
    Activations Density 0.040%

    No Known Activations