© 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. 58002
    Prev
    Next
    INDEX
    Explanations

    in partnership with

    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
     Teh
    -0.11
    解æĶ¾
    -0.10
    pher
    -0.09
    anean
    -0.08
    enis
    -0.08
    lemn
    -0.08
    å°ļ
    -0.08
    水管
    -0.08
    åIJĵ
    -0.08
    OGLE
    -0.08
    POSITIVE LOGITS
    ç§Ń
    0.10
    ä¸į解
    0.10
    çŁ¥
    0.09
    æŁ¬
    0.09
    桨
    0.09
    åıªå¾Ĺ
    0.09
    å¸ĮæľĽèĩªå·±
    0.09
    éļĶ
    0.09
    Ñıд
    0.08
    _passwd
    0.08
    Activations Density 0.103%

    No Known Activations