© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52772
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    æľĽ
    -0.10
    带走
    -0.08
    ody
    -0.08
     basically
    -0.08
    æįİ
    -0.08
    ugi
    -0.07
    åħ¨ä¸ĸçķĮ
    -0.07
    weet
    -0.07
    eof
    -0.07
     forever
    -0.07
    POSITIVE LOGITS
    æĥĨ
    0.10
    VIRTUAL
    0.09
    ë©Ģ
    0.09
     vice
    0.09
    hower
    0.09
    æĽ²æĬĺ
    0.09
    ä¸İæĹ¶ä¿±
    0.09
    çİ°å®ŀçĶŁæ´»
    0.09
    è¯ģåĪ¸æĬķèµĦ
    0.09
    ynes
    0.08
    Activations Density 0.086%

    No Known Activations