© 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. 5026
    Prev
    Next
    INDEX
    Explanations

    published, released, assist, co-chair

    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
    æݾ
    -0.09
     american
    -0.08
    è´
    -0.08
    çĥŁçģ«
    -0.08
    çī¡
    -0.08
     Invasion
    -0.08
    çļĸ
    -0.08
    å¤ļ人
    -0.08
    é»ĦçŁ³
    -0.08
    ấ
    -0.07
    POSITIVE LOGITS
    åIJĦåĽ½
    0.16
    æĪIJåijĺåĽ½
    0.14
    åľ¨åħ¨çIJĥ
    0.12
    è·¨åĽ½
    0.12
    èģĶåIJĪåĽ½
    0.12
    UNCT
    0.11
    审议
    0.10
    åħ¨çIJĥ
    0.10
    ä¸īåĽ½
    0.09
    åħ¨çIJĥç»ıæµİ
    0.09
    Activations Density 0.365%

    No Known Activations