© 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. 22835
    Prev
    Next
    INDEX
    Explanations

    games on different platforms

    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
    ç§ģæľį
    -0.10
    ITES
    -0.09
    åIJ¬å¾Ĺ
    -0.09
     Ingram
    -0.09
    StringRef
    -0.09
    newInstance
    -0.08
    å¦Ļ
    -0.08
    éģ¥æݧ
    -0.08
    itle
    -0.08
    ouro
    -0.08
    POSITIVE LOGITS
    (platform
    0.10
    åij¼åĶ¤
    0.10
    å¹³åı°
    0.10
    è·Ľ
    0.10
    REW
    0.10
    imei
    0.09
    éļ¶å±ŀ
    0.09
    ä¸ŃåĽ½å¤§éĻĨ
    0.09
    ä¸Ń央
    0.09
    ä»ĺåĩº
    0.09
    Activations Density 0.358%

    No Known Activations