© 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. 31734
    Prev
    Next
    INDEX
    Explanations

    materials and applications

    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
    LLU
    -0.09
    åIJĦæľī
    -0.09
    ongan
    -0.09
    çªģ
    -0.08
    å¤ĸåĩº
    -0.08
     Ibrahim
    -0.08
    å¾Ī容æĺĵ
    -0.08
    汨
    -0.08
    quisite
    -0.08
    chants
    -0.08
    POSITIVE LOGITS
    çŃīé¢ĨåŁŁ
    0.11
    .cz
    0.09
    å¼ĢåĬŀ
    0.09
    _odd
    0.08
    纷纷
    0.08
    ç¢Ł
    0.08
    游æĪıä¸Ń
    0.08
    ForObject
    0.08
    è¾Ł
    0.08
    家çĶ¨
    0.08
    Activations Density 0.745%

    No Known Activations