© 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. 35506
    Prev
    Next
    INDEX
    Explanations

    behind schedule

    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
    éĢĢå½¹
    -0.09
    çĶŁæ¶¯
    -0.09
    .hd
    -0.09
    åľ¨æ·±åľ³
    -0.09
    Toolkit
    -0.09
    -basket
    -0.09
    endir
    -0.09
     Rout
    -0.09
    é¦ĸ次
    -0.08
    SHIFT
    -0.08
    POSITIVE LOGITS
    è·Łä¸įä¸Ĭ
    0.13
     backlog
    0.12
    éľŃ
    0.10
    赶ä¸Ĭ
    0.10
    èIJ½åIJİ
    0.10
     catching
    0.10
     catch
    0.09
     lag
    0.09
    èIJ½ä¸ĭ
    0.09
    æĮģå¹³
    0.09
    Activations Density 0.056%

    No Known Activations