© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38060
    Prev
    Next
    INDEX
    Explanations

    marching bands, camps, and parades

    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
     же
    -0.11
    arker
    -0.10
    ting
    -0.10
    ondo
    -0.09
    rador
    -0.09
    大å¹ħ度
    -0.09
    neath
    -0.09
    èµľ
    -0.08
    ACTIVE
    -0.08
    à¸Ļà¸Ńà¸Ļ
    -0.08
    POSITIVE LOGITS
    itecture
    0.12
    ernet
    0.10
    etti
    0.10
    æĺ´
    0.10
    ses
    0.09
    ç°ĩ
    0.09
    (es
    0.09
    andise
    0.09
    itect
    0.09
    andle
    0.09
    Activations Density 0.017%

    No Known Activations