© 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. 34180
    Prev
    Next
    INDEX
    Explanations

    code after keywords

    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
    åŁºæľ¬è¦ģæ±Ĥ
    -0.07
    inat
    -0.07
    [top
    -0.07
    ob
    -0.07
    sonian
    -0.07
    ieur
    -0.06
    -terminal
    -0.06
    afone
    -0.06
    terminal
    -0.06
    ...
    -0.06
    POSITIVE LOGITS
    rade
    0.08
    EFE
    0.07
    æĽ´å¤ļåĽŀçŃĶ
    0.07
    nowrap
    0.07
    åīįè¡ĮçļĦ
    0.07
    Ľ
    0.07
     ofre
    0.07
    åıĬæľīåħ³
    0.06
    ÐłÐ¡
    0.06
    ä¸İç»´æĬ¤
    0.06
    Activations Density 0.025%

    No Known Activations