© 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. 27469
    Prev
    Next
    INDEX
    Explanations

    names beginning with Rita or Rit

    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
    predicate
    -0.09
    ä¸įäºĨ
    -0.09
    ennifer
    -0.09
    ä¸Ŀä¸Ŀ
    -0.09
    _predicate
    -0.09
    ëħIJ
    -0.08
    /cmd
    -0.08
    леж
    -0.08
     Malta
    -0.08
    æ·±çŁ¥
    -0.08
    POSITIVE LOGITS
    çĪ·
    0.09
    keeper
    0.09
    ä¾Ī
    0.09
    .multipart
    0.09
    marshal
    0.09
    èļĤ
    0.08
    webkit
    0.08
    ìĮį
    0.08
    ะ
    0.08
    ä¸Ńåħ³æĿij
    0.08
    Activations Density 0.003%

    No Known Activations