© 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. 18488
    Prev
    Next
    INDEX
    Explanations

    instruction to look below

    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
     içinde
    -0.09
    æģ«
    -0.08
     sequence
    -0.08
    Ath
    -0.08
    ÙĦاØŃ
    -0.08
    åħ¨åŁŁ
    -0.08
    åİĤ
    -0.08
    åħ¬åı¸åľ¨
    -0.08
     Prep
    -0.08
    æĶ¯æŁ±
    -0.08
    POSITIVE LOGITS
    æĪĸæĺ¯
    0.10
    osto
    0.09
    ubo
    0.09
     Gow
    0.09
    综åIJĪåĪ©çĶ¨
    0.09
    å¼ĢèįĴ
    0.09
    èIJ¼
    0.09
    ADE
    0.09
    æľ¬çĿĢ
    0.09
    该æĢİä¹Ī
    0.08
    Activations Density 0.001%

    No Known Activations