© 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. 57360
    Prev
    Next
    INDEX
    Explanations

    people who organize or create

    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
     Orch
    -0.09
    licer
    -0.08
    è¾ĥéķ¿
    -0.08
    orch
    -0.08
    едÑĮ
    -0.08
    ä¸Ńå°ıåŀĭ
    -0.08
     longer
    -0.08
    linger
    -0.08
    ä»»æľŁ
    -0.08
    å°ıå§IJ
    -0.08
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.12
    å§ĭç»Īä¿ĿæĮģ
    0.10
    åĿļä¿¡
    0.10
    åħ¼
    0.10
    èIJ¥åķĨ
    0.09
    ersh
    0.09
    ÙħÙĪر
    0.09
    çĨĻ
    0.09
    åĿļ
    0.08
    æ·±çŁ¥
    0.08
    Activations Density 0.056%

    No Known Activations