© 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. 25010
    Prev
    Next
    INDEX
    Explanations

    genome program

    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
    éŁ
    -0.08
    ãĤ¯
    -0.06
    åıĪ称为
    -0.06
    abar
    -0.06
    å¸Ĥåľºè¡Įæĥħ
    -0.06
    áĪĽ
    -0.06
    æĻı
    -0.06
     VERS
    -0.06
    çIJĽ
    -0.06
    常åĬ¡å§Ķåijĺä¼ļ
    -0.05
    POSITIVE LOGITS
    ryn
    0.08
    èĥ¤
    0.08
    jing
    0.08
    ÙĪارد
    0.08
    ÛĮÙĨÚ¯
    0.08
    coder
    0.08
    arians
    0.08
    çĻ½éľ²
    0.08
    ÃŃp
    0.07
    @$
    0.07
    Activations Density 0.151%

    No Known Activations