© 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. 50186
    Prev
    Next
    INDEX
    Explanations

    green light to

    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
    ä½Ĩä¸įéĻIJ
    -0.10
    è·Ĺ
    -0.09
    ainen
    -0.09
    éģĵçIJĨ
    -0.09
    ationally
    -0.09
    èĬŃ
    -0.09
    yne
    -0.09
    å¤Ļ
    -0.09
    å¸ĸ
    -0.08
    oms
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.09
    å·®çĤ¹
    0.09
     pads
    0.09
    ted
    0.09
    pped
    0.09
    人åĬĽ
    0.09
    td
    0.08
    eg
    0.08
    è¸ı
    0.08
    äºŃ
    0.08
    Activations Density 0.012%

    No Known Activations