© 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. 61906
    Prev
    Next
    INDEX
    Explanations

    hotel names

    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
    lain
    -0.09
    ç¾Ĭ
    -0.09
    kea
    -0.09
    assis
    -0.09
    å¾Ĺä½ı
    -0.08
    ä¸ĭåįķ
    -0.08
     оÑĤдÑĭÑħ
    -0.08
    ä¿ĥæĪIJ
    -0.08
    ugu
    -0.08
    èį¤
    -0.08
    POSITIVE LOGITS
    æĪ·ç±į
    0.10
    çļ±çº¹
    0.09
    夸
    0.09
    èŀ«
    0.09
    èħĨ
    0.09
    å¸Ĥåľºç«ŀäºī
    0.08
    é¢Īéĥ¨
    0.08
    ardown
    0.08
    olds
    0.08
    è·¨åĽ½
    0.08
    Activations Density 0.029%

    No Known Activations