© 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. 4748
    Prev
    Next
    INDEX
    Explanations

    satellite and GIS operations

    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
     esk
    -0.09
    amp
    -0.09
    adow
    -0.09
     tre
    -0.09
    å¾ģä¿¡
    -0.09
    äºĨä¸Ģåı£
    -0.08
    éĵ¢
    -0.08
    ç¾Ĭ
    -0.08
     Jeb
    -0.08
    .ax
    -0.08
    POSITIVE LOGITS
    å§Ĭ妹
    0.10
    çľĭå¾Ĺ
    0.10
    æĬĢæľ¯çłĶåıij
    0.09
     Curtain
    0.09
    eltas
    0.09
    _GL
    0.09
    praak
    0.09
    /lic
    0.09
    shade
    0.09
    é¢Ĩçķ¥
    0.08
    Activations Density 0.086%

    No Known Activations