© 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. 3987
    Prev
    Next
    INDEX
    Explanations

    numeric sequences after words

    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
    ìľĦì¹ĺ
    -0.09
    -placement
    -0.08
    _placement
    -0.08
    __["
    -0.08
    CRET
    -0.08
    placement
    -0.08
    ::__
    -0.07
    ÐIJÐŁ
    -0.07
     fok
    -0.07
     Szk
    -0.07
    POSITIVE LOGITS
     majority
    0.08
     irregular
    0.07
    æĺİæĺ¾
    0.07
    è¯Ĩ
    0.07
    ä¸Ķåľ¨
    0.07
     наиб
    0.07
    æľĢèĥ½
    0.06
    æĺİç¡®
    0.06
    çĸijä¼¼
    0.06
    exclude
    0.06
    Activations Density 0.010%

    No Known Activations