© 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. 30976
    Prev
    Next
    INDEX
    Explanations

    dis- prefix denoting negation or separation

    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
    reeze
    -0.10
    gether
    -0.10
    ../../
    -0.10
    oretical
    -0.10
    æįĤ
    -0.10
    DataExchange
    -0.09
    çĦIJ
    -0.09
    们
    -0.09
    PING
    -0.09
     ((__
    -0.09
    POSITIVE LOGITS
    liest
    0.09
    far
    0.09
    èĤ¢
    0.09
    念
    0.09
    otropic
    0.09
    ÂŃt
    0.09
    lands
    0.08
    æĴĴ
    0.08
     наб
    0.08
     Hoffman
    0.08
    Activations Density 0.019%

    No Known Activations