© 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. 2925
    Prev
    Next
    INDEX
    Explanations

    Wesley Clark Martin Bor

    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
    iple
    -0.09
    ä»İä¸ļ
    -0.09
    idot
    -0.09
    ç¾İå¾·
    -0.09
    lef
    -0.09
    mith
    -0.09
     sẵn
    -0.08
    æĪ¢
    -0.08
    íİľ
    -0.08
    DrawerToggle
    -0.08
    POSITIVE LOGITS
    onian
    0.11
    oke
    0.09
    åĽĽåįģ
    0.09
    ä¸ĭ鼨
    0.09
    ç¢Į
    0.09
    ically
    0.08
    æ§Į
    0.08
     вÑĭÑĢажен
    0.08
    olia
    0.08
    ÙĬات
    0.08
    Activations Density 0.004%

    No Known Activations