© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32275
    Prev
    Next
    INDEX
    Explanations

    taking pictures of

    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
    official
    -0.10
    buster
    -0.09
    Lou
    -0.09
    è¡·
    -0.08
    èħĶ
    -0.08
    çľĩ
    -0.08
    羡
    -0.08
    LOY
    -0.08
    èIJ¥åķĨ
    -0.08
    croll
    -0.08
    POSITIVE LOGITS
    å¥ķ
    0.09
    fte
    0.09
    fter
    0.08
    æĸ°é²ľ
    0.08
    iso
    0.08
    å¹¶åIJij
    0.08
    é¢Ĩ
    0.08
    æ£ļ
    0.08
     fetus
    0.07
    ê°ģ
    0.07
    Activations Density 0.062%

    No Known Activations