© 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. 40132
    Prev
    Next
    INDEX
    Explanations

    good news

    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
    OLS
    -0.09
    ead
    -0.09
    walker
    -0.09
    ä¹ĥ
    -0.09
    æ¸ħæĺİ
    -0.08
     cute
    -0.08
    åIJĪä¸Ģ
    -0.08
    ottage
    -0.08
    éħ
    -0.08
    æĺİæĺŁ
    -0.08
    POSITIVE LOGITS
    alah
    0.09
    çĶ¨å·¥
    0.09
    çĮ®
    0.08
    èī¯
    0.08
    irc
    0.08
    smith
    0.08
    çľ¼éĩĮ
    0.08
    _softc
    0.08
    åľ¨äºİ
    0.08
    ely
    0.08
    Activations Density 0.004%

    No Known Activations