© 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. 39439
    Prev
    Next
    INDEX
    Explanations

    subdomain or subdirectory

    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
    å°±è·Ł
    -0.10
    å°ıå¿ĥ翼翼
    -0.10
    ç¨įå¾®
    -0.10
    å°ıå¿ĥ
    -0.09
    èĭŀ
    -0.09
    bum
    -0.09
    æĵ¦æĭŃ
    -0.09
    uite
    -0.09
    umm
    -0.09
     оÑĤкÑĢÑĭÑĤ
    -0.09
    POSITIVE LOGITS
    é¢ĨåŁŁ
    0.10
    éłĺåŁŁ
    0.10
    CLR
    0.09
    é¢ĨåŁŁçļĦ
    0.09
    è´¢æĶ¿éĥ¨
    0.09
     Pok
    0.09
    ä¸Ģéģĵ
    0.08
    ç»®
    0.08
    æĭ¼
    0.08
     CLR
    0.08
    Activations Density 0.067%

    No Known Activations