© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51349
    Prev
    Next
    INDEX
    Explanations

    "the" 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
    赫
    -0.09
    gettext
    -0.09
    isan
    -0.09
     зав
    -0.09
    稳æŃ¥
    -0.08
    вл
    -0.08
    .logged
    -0.08
    亲å¯Ĩ
    -0.08
    è¹Ĵ
    -0.08
    ancies
    -0.08
    POSITIVE LOGITS
    ssi
    0.10
    ç¯ĵ
    0.10
    诱æĥij
    0.10
     sooner
    0.10
    áºŃu
    0.09
    æĹ©æĻļ
    0.09
    èĴĮ
    0.08
    ä¸ĵçıŃ
    0.08
    oret
    0.08
     Bent
    0.08
    Activations Density 0.175%

    No Known Activations