© 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. 58199
    Prev
    Next
    INDEX
    Explanations

    presence

    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
     medi
    -0.09
    说å®ŀ
    -0.09
    Segue
    -0.09
    enville
    -0.09
    åIJ¬èµ·æĿ¥
    -0.08
    atab
    -0.08
    åĪĨå·¥
    -0.08
     Prim
    -0.08
    Exclusive
    -0.08
    åĴĮå¹³
    -0.08
    POSITIVE LOGITS
     presence
    0.17
    presence
    0.16
    Presence
    0.14
    åľ¨éĤ£éĩĮ
    0.14
     présence
    0.13
     ÙħÙĪجÙĪد
    0.13
     Presence
    0.13
     налиÑĩии
    0.13
    éĤ£åĦ¿
    0.13
     presença
    0.12
    Activations Density 0.116%

    No Known Activations