© 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. 11880
    Prev
    Next
    INDEX
    Explanations

    years ending in 7

    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
    aland
    -0.11
    åĪĬçī©
    -0.09
    åı¯æĥľ
    -0.09
    ç¢ĵ
    -0.09
    椿
    -0.09
    ç½ļ
    -0.08
     Rap
    -0.08
    rena
    -0.08
    ä¸įåĩº
    -0.08
    çłĶ究æĪIJæŀľ
    -0.08
    POSITIVE LOGITS
    æĤī
    0.09
     Sag
    0.09
    çĭł
    0.09
    ä¾ĺ
    0.09
    è¿Ļä¸Ģå¹´
    0.09
     disco
    0.09
     Calder
    0.09
    -assets
    0.08
    æģļ
    0.08
     reply
    0.08
    Activations Density 0.186%

    No Known Activations