© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    type

    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
    è¡·
    -0.10
    æĬĬæı¡
    -0.09
    çĸĶ
    -0.09
    å¤ļå°ij
    -0.08
    åĤį
    -0.08
    æIJª
    -0.08
    ä¼ı
    -0.08
    dbh
    -0.08
    æ®·
    -0.08
    horse
    -0.08
    POSITIVE LOGITS
    è´¨éĩıéĹ®é¢ĺ
    0.11
    è¿Ļæĸ¹éĿ¢
    0.10
    æĽ³
    0.10
     pes
    0.09
    æĩĴ
    0.09
    举
    0.09
    åıĮéĩį
    0.09
    ancell
    0.09
    éª
    0.08
     heavily
    0.08
    Activations Density 0.163%

    No Known Activations