© 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. 61898
    Prev
    Next
    INDEX
    Explanations

    company names after "called" or "company"

    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
    æĿ¯
    -0.10
    SKIP
    -0.09
    ä¸į对
    -0.09
    欺è¯Ī
    -0.09
    ä¼ļåIJĮ
    -0.09
    è´¿
    -0.09
    feit
    -0.09
     choc
    -0.09
    çªį
    -0.08
    ä¼łæŁĵ
    -0.08
    POSITIVE LOGITS
    çľģæĶ¿åºľ
    0.10
    çļĦåĪ©çĽĬ
    0.09
    çĶ³æĬ¥
    0.09
    éĢģåİ»
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    åħ¥èĤ¡
    0.09
    çļĦåģļæ³ķ
    0.08
    涧
    0.08
    为åħ¶
    0.08
    庵
    0.08
    Activations Density 0.027%

    No Known Activations