© 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. 48876
    Prev
    Next
    INDEX
    Explanations

    within

    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
    éĢı
    -0.10
    ä¼´
    -0.10
    _COMPLETE
    -0.09
    å¾ĹçĽĬ
    -0.09
    ä»İä¸ļ
    -0.08
    åľ¨è¿Ļç§į
    -0.08
    .getResult
    -0.08
    inces
    -0.08
    æĹ¥åľ¨
    -0.08
     VIA
    -0.08
    POSITIVE LOGITS
    ä¹ĭåĨħ
    0.12
     confines
    0.11
    -addon
    0.10
    .scope
    0.10
    æ¡Ĩæŀ¶
    0.10
    çķĮéĻIJ
    0.10
    çļĦæŶéĹ´éĩĮ
    0.10
    社ä¼ļå®ŀè·µ
    0.10
     framework
    0.09
     Walls
    0.09
    Activations Density 0.147%

    No Known Activations