© 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. 57025
    Prev
    Next
    INDEX
    Explanations

    target stores

    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
    伪
    -0.09
    åªļ
    -0.09
     гоÑģ
    -0.09
     Minds
    -0.08
    .liferay
    -0.08
    æĪijåľ¨
    -0.08
    gow
    -0.08
    alion
    -0.08
    å¸ħ
    -0.08
    -kit
    -0.08
    POSITIVE LOGITS
    .Strict
    0.10
    æ´»å¾Ĺ
    0.09
    èł¹
    0.09
    asil
    0.09
     Corporation
    0.09
    æĬĬä»ĸ
    0.08
    è¶ħå¸Ĥ
    0.08
    é«ĺåĩº
    0.08
    袱
    0.08
    åĹħ
    0.08
    Activations Density 0.004%

    No Known Activations