© 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. 57118
    Prev
    Next
    INDEX
    Explanations

    24/7

    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
    ffield
    -0.10
    éļIJéļIJ
    -0.09
    ocard
    -0.09
    GBP
    -0.09
    kie
    -0.09
     Osman
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    éļ¾æĢª
    -0.08
    imals
    -0.08
    nty
    -0.08
    POSITIVE LOGITS
    OLT
    0.09
    æ¯Ľ
    0.09
    åľ°çIJĥä¸Ĭ
    0.08
    è°ģéĥ½
    0.08
    _CHO
    0.08
     hazırl
    0.08
     Blanch
    0.08
    ç»´æĬ¤
    0.08
    æ¦Ń
    0.08
     Milo
    0.07
    Activations Density 0.004%

    No Known Activations