© 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. 5739
    Prev
    Next
    INDEX
    Explanations

    maximum amount

    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
    ead
    -0.10
    èĥĮä¸Ĭ
    -0.10
    oji
    -0.09
    çıĻ
    -0.09
    足
    -0.09
    heets
    -0.09
    gend
    -0.09
    oose
    -0.09
    rial
    -0.09
    æļĿ
    -0.09
    POSITIVE LOGITS
    imum
    0.13
    IMUM
    0.12
    èİ«è¿ĩäºİ
    0.12
    -ever
    0.11
    imal
    0.11
    éĻIJ度
    0.11
    =max
    0.10
    imizer
    0.10
    (Max
    0.10
    Reached
    0.09
    Activations Density 0.105%

    No Known Activations