© 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. 62987
    Prev
    Next
    INDEX
    Explanations

    huge amounts

    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
     Paths
    -0.09
    好åĿı
    -0.09
    orate
    -0.09
    etsk
    -0.09
    adem
    -0.08
    irm
    -0.08
     schön
    -0.08
    exact
    -0.08
    ieren
    -0.08
    大èĥĨ
    -0.08
    POSITIVE LOGITS
    itarian
    0.13
     amounts
    0.13
    æĹłæ¯Ķ
    0.11
    身躯
    0.10
    巨大çļĦ
    0.10
     amount
    0.10
    oted
    0.10
    ä¸ĢåĽ¢
    0.09
    åīįæıIJæĺ¯
    0.09
    /fast
    0.09
    Activations Density 0.032%

    No Known Activations