© 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. 1174
    Prev
    Next
    INDEX
    Explanations

    commitment to

    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
    åij³
    -0.09
    udd
    -0.09
    ä½ŀ
    -0.09
    ius
    -0.09
    ä¸Ģå°ģ
    -0.08
    åĮĸè¿Ľç¨ĭ
    -0.08
    trad
    -0.08
    ton
    -0.08
    /un
    -0.08
    è¿Ļ段
    -0.08
    POSITIVE LOGITS
    anine
    0.10
     далÑĮ
    0.09
    å¦Ĥä¸ĭ
    0.09
    ted
    0.09
    大éģĵ
    0.09
    äºĭåIJİ
    0.08
    人åĬĽ
    0.08
    åIJİèĢħ
    0.08
    /from
    0.08
    大è·Į
    0.08
    Activations Density 0.006%

    No Known Activations