© 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. 27980
    Prev
    Next
    INDEX
    Explanations

    Islamic terms of endearment

    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
    eren
    -0.09
    çĹĤ
    -0.09
    åŁŃ
    -0.09
    ãĤ»ãĥ³
    -0.09
    JECTED
    -0.09
    AREN
    -0.08
    nych
    -0.08
    é«ĺ级
    -0.08
    oplan
    -0.08
    æľ¬èĥ½
    -0.08
    POSITIVE LOGITS
    æĿ¯
    0.10
    èĩ»
    0.09
     Scrap
    0.09
    äºĨå¾Īå¤ļ
    0.09
    踪
    0.09
    ç¿
    0.09
    追踪
    0.09
    cup
    0.09
    leen
    0.08
    稳
    0.08
    Activations Density 0.037%

    No Known Activations