© 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. 30600
    Prev
    Next
    INDEX
    Explanations

    I want

    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
    å°±æľīäºĨ
    -0.09
     somehow
    -0.09
    âĨ³
    -0.09
    awl
    -0.08
    åĩĮ
    -0.08
    羣æĺ¯
    -0.08
    æłijæŀĿ
    -0.08
    .getCount
    -0.08
    afia
    -0.08
     suddenly
    -0.08
    POSITIVE LOGITS
    çŁ¥æĥħ
    0.11
    æĻĵå¾Ĺ
    0.11
    å°Ĭéĩį
    0.11
    深深
    0.11
    ä¹ŁçŁ¥éģĵ
    0.10
    æī¿è®¤
    0.09
    åħħåĪĨèĤ¯å®ļ
    0.09
     Cave
    0.09
    æ·±çŁ¥
    0.09
     conced
    0.09
    Activations Density 0.046%

    No Known Activations