© 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. 49871
    Prev
    Next
    INDEX
    Explanations

    Digimap and BCF store details

    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
    åĪĨæīĭ
    -0.10
    å¼±
    -0.10
    å°ģ
    -0.08
    IAS
    -0.08
    апÑĢ
    -0.08
     GPLv
    -0.08
     Higgins
    -0.08
    ftime
    -0.08
    å·¦æīĭ
    -0.08
    (PR
    -0.08
    POSITIVE LOGITS
    该åħ¬åı¸
    0.12
    äºĨä»ĸçļĦ
    0.12
    æĪij说
    0.10
     اÙĦتابعة
    0.10
    çīĮåŃIJ
    0.09
    ç³»åĪĹ产åĵģ
    0.09
    ä»ĸçļĦ
    0.09
    æĪķ
    0.09
     products
    0.09
    å§ĭäºİ
    0.09
    Activations Density 0.154%

    No Known Activations