© 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. 47807
    Prev
    Next
    INDEX
    Explanations

    price and value

    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
    anth
    -0.08
    ãģ£ãģ
    -0.08
    amma
    -0.08
    æİĮ
    -0.08
    igne
    -0.08
    èµĤ
    -0.08
    .heading
    -0.08
    æ·±æ·±åľ°
    -0.08
    æ·±åĪ»çļĦ
    -0.07
    favor
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģéĥ¨åĪĨ
    0.10
    agli
    0.10
     ấy
    0.10
    è¿Ļ座åŁİå¸Ĥ
    0.10
    ãģ¾ãģ¾
    0.09
    ä¸įä½³
    0.09
    ç§įç§į
    0.09
    æ¼ĵ
    0.09
     sÆ°
    0.09
    æ°ı
    0.09
    Activations Density 0.111%

    No Known Activations