© 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. 35240
    Prev
    Next
    INDEX
    Explanations

    that followed by a noun

    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
    éĤ£
    -0.14
    éĤ£ä¸ªäºº
    -0.13
    éĤ£ä¸ª
    -0.13
    éĤ£äºº
    -0.13
    éĤ£ä½ł
    -0.13
    éĤ£æŶ
    -0.12
    éĤ£åıª
    -0.12
    éĤ£æĺ¯
    -0.12
    éĩĩæijĺ
    -0.11
    éĤ£ä½į
    -0.11
    POSITIVE LOGITS
     this
    0.12
    :this
    0.11
    (this
    0.10
    this
    0.10
    è¿Ļä¸ĢçĤ¹
    0.10
    è¿ĻçĤ¹
    0.09
    <this
    0.09
    æŁIJä¸Ģ
    0.09
    è¿Ļ份
    0.09
    >this
    0.09
    Activations Density 0.112%

    No Known Activations