© 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. 48622
    Prev
    Next
    INDEX
    Explanations

    common practice

    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
    çĸı
    -0.11
    åıĮåıĮ
    -0.10
    å³Ļ
    -0.10
    ç§įç§į
    -0.09
    ãĤĵãģª
    -0.09
    éį
    -0.09
    thed
    -0.08
    æľīåĬ©äºİ
    -0.08
     пиÑĤ
    -0.08
    åIJ¦
    -0.08
    POSITIVE LOGITS
    æīĵçł´
    0.10
     имеÑĤÑĮ
    0.09
    èµ°åĩº
    0.09
     иÑģполÑĮзоваÑĤÑĮ
    0.09
    çIJĨ解
    0.09
     lone
    0.09
     to
    0.09
     вÑĭбÑĢаÑĤÑĮ
    0.08
    人们对
    0.08
    æīĵå¼Ģ
    0.08
    Activations Density 0.135%

    No Known Activations