© 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. 18465
    Prev
    Next
    INDEX
    Explanations

    only

    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
     же
    -0.09
     ÑĢай
    -0.09
    ãģ¡ãĤĩãģĨãģ©
    -0.09
    ãģĿãĤĤãģĿãĤĤ
    -0.09
    ä¹ĭæīĢ以
    -0.09
    weise
    -0.09
    åįģå¹´åīį
    -0.09
     دائÙħا
    -0.08
    rors
    -0.08
    -Cs
    -0.08
    POSITIVE LOGITS
    ENO
    0.09
    æĺ¯ä¸Ģç§į
    0.09
    deserialize
    0.08
    åĬĽè¿ĺæĺ¯
    0.08
    对æİ¥
    0.08
    设æĸ½å»ºè®¾
    0.08
    ä¸įèĪį
    0.08
    èĩªå¦Ĥ
    0.08
    ä¸Ģ页
    0.08
    åħ³äºİæĪij们
    0.08
    Activations Density 0.058%

    No Known Activations