© 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. 62246
    Prev
    Next
    INDEX
    Explanations

    financial tickers and symbols

    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
    è¹´
    -0.10
    è¯Ŀ
    -0.10
    åIJĬ
    -0.09
    翳
    -0.09
    Ø·ÙĪÙĦ
    -0.09
    ä¸įæİĴéĻ¤
    -0.09
     ÙħÙĪا
    -0.09
    æĹ¥å¸¸çĶŁæ´»
    -0.09
    iele
    -0.08
    Pitch
    -0.08
    POSITIVE LOGITS
    åįĩ
    0.09
    BAT
    0.09
    erval
    0.08
    注æĦıåĬĽ
    0.08
    æŁĦ
    0.08
     BCH
    0.08
    ucas
    0.08
    _loader
    0.08
    对æİ¥
    0.08
     popular
    0.08
    Activations Density 0.062%

    No Known Activations