© 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. 19017
    Prev
    Next
    INDEX
    Explanations

    National Park Service

    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
    åĴĮ个人
    -0.10
    âĸ¶
    -0.09
    çĢĽ
    -0.09
     breakout
    -0.09
    å·¥ä¸ļ大åѦ
    -0.09
    å¸ĤæĶ¿åºľ
    -0.09
    æ²ģ
    -0.09
    око
    -0.08
    ä¸Ģç¬ij
    -0.08
    å¸Ĥ人大
    -0.08
    POSITIVE LOGITS
    inar
    0.08
     dop
    0.08
    è¯įæĿ¡
    0.08
    trys
    0.08
    é¢Ł
    0.08
     Moor
    0.08
    gid
    0.08
    Descriptors
    0.08
    opens
    0.08
    otten
    0.08
    Activations Density 0.010%

    No Known Activations