© 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. 17530
    Prev
    Next
    INDEX
    Explanations

    contrast or contrast-enhanced

    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
    ities
    -0.10
    åİŁåĽłæĺ¯
    -0.10
    ÑĮÑı
    -0.09
    naire
    -0.08
    éħįå¥Ĺ设æĸ½
    -0.08
    ses
    -0.08
     Bahamas
    -0.08
    itary
    -0.08
    оÑĤоÑĢ
    -0.08
    itude
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    é²ľæĺİ
    0.10
    mere
    0.10
    dere
    0.10
    tape
    0.09
    วà¸ĩ
    0.09
    ä¼ļç»Ļ
    0.09
    大èĥĨ
    0.09
    åĪĨæĺİ
    0.09
    worthy
    0.08
    Activations Density 0.014%

    No Known Activations