© 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. 49360
    Prev
    Next
    INDEX
    Explanations

    usual following numbers or specific 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
    волÑĮ
    -0.08
    _ten
    -0.08
    минÑĥ
    -0.08
    çļĦè¾ĵåĩº
    -0.07
    лек
    -0.07
     bebas
    -0.07
    µľ
    -0.07
    epen
    -0.07
    abah
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.07
    POSITIVE LOGITS
     usual
    0.12
    常è§ĦçļĦ
    0.12
     typical
    0.12
    æłĩåĩĨçļĦ
    0.12
    åħ¸åŀĭçļĦ
    0.12
    usual
    0.11
    æĥ¯ä¾ĭ
    0.11
    classic
    0.11
    ç»ıåħ¸çļĦ
    0.11
    常è§Ħ
    0.11
    Activations Density 0.442%

    No Known Activations