© 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. 58574
    Prev
    Next
    INDEX
    Explanations

    Ye, Yeh, Yeap, Yeap, Yeap

    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
    ed
    -0.09
    åIJĦæł·
    -0.08
    à¹Ģà¸ī
    -0.08
    rid
    -0.08
    æµģåŁŁ
    -0.08
    à¸ļำ
    -0.08
    اة
    -0.08
    å¸ı
    -0.08
     binder
    -0.08
    apter
    -0.08
    POSITIVE LOGITS
    enary
    0.09
    enes
    0.09
    å¾Ģå¤ĸ
    0.09
    åıĹãģij
    0.08
    _SID
    0.08
     Ones
    0.08
    æ´ĹèĦ¸
    0.08
    ãģªãģĮãĤī
    0.08
    ensch
    0.08
    ä»ħ代表
    0.08
    Activations Density 0.014%

    No Known Activations