© 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. 22277
    Prev
    Next
    INDEX
    Explanations

    an eyebrow

    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
    åħ¶ä»ĸ
    -0.08
     Ñĥзн
    -0.08
    å°±è¿ŀ
    -0.07
    è¿ĻäºĽéĥ½æĺ¯
    -0.07
     other
    -0.07
    è¿Ļä¸ĢåĪĩ
    -0.07
    _macros
    -0.06
    ellow
    -0.06
    åIJ¬äºĨ
    -0.06
    m
    -0.06
    POSITIVE LOGITS
    CallableWrapper
    0.11
     arsch
    0.10
    æĸĽ
    0.10
    åºĦæĿij
    0.10
     milfs
    0.10
    æĮ½åĽŀ
    0.10
    .SizeType
    0.10
    槿
    0.10
    Intialized
    0.10
    èĶ»
    0.09
    Activations Density 4.157%

    No Known Activations