© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16413
    Prev
    Next
    INDEX
    Explanations

    series followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ming
    -0.08
    ammad
    -0.06
    两åIJį
    -0.06
    arma
    -0.06
    äºĨçīĩåĪ»
    -0.06
    两çĤ¹
    -0.06
    äºĮåĪĨ
    -0.06
    ä¸ĢéĹª
    -0.06
    æ··åIJĪ
    -0.06
    agg
    -0.06
    POSITIVE LOGITS
    ç³»åĪĹ
    0.23
     series
    0.22
    series
    0.19
    ç³»åĪĹçļĦ
    0.19
    ãĤ·ãĥªãĥ¼ãĤº
    0.19
     ÑģеÑĢиÑı
    0.18
    çļĦä¸Ģç³»åĪĹ
    0.18
    ä¸Ģç³»åĪĹ
    0.18
     ÑģеÑĢии
    0.17
    -series
    0.17
    Activations Density 0.595%

    No Known Activations