© 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. 23676
    Prev
    Next
    INDEX
    Explanations

    by followed by a verb

    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
    влека
    -0.08
    preh
    -0.07
    ັàºĻ
    -0.07
    _FIND
    -0.07
    æľªå¿ħ
    -0.07
    çļĦæķ°æį®æĺ¾ç¤º
    -0.06
     swallowed
    -0.06
    olves
    -0.06
     evolves
    -0.06
     salvagu
    -0.06
    POSITIVE LOGITS
     using
    0.10
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.10
     applying
    0.10
    ä»Ģä¹Īåij¢
    0.10
     virtue
    0.10
    æ¯Ķè¾ĥå°ı
    0.10
     way
    0.09
     simply
    0.09
     firstly
    0.08
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.08
    Activations Density 0.200%

    No Known Activations