© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30276
    Prev
    Next
    INDEX
    Explanations

    n followed by dash

    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
    ac
    -0.07
     (
    -0.06
    æķ£
    -0.06
    é
    -0.06
    izzy
    -0.06
    -0.06
     )
    -0.05
    aus
    -0.05
    ucher
    -0.05
     =
    -0.05
    POSITIVE LOGITS
    Ñģполни
    0.08
    -Allow
    0.08
    ">@
    0.08
    inesi
    0.08
     oficia
    0.08
    "';
    0.08
    åĮ»éĻ¢è¿Ľè¡Į
    0.08
     Coro
    0.08
    **–
    0.08
    leven
    0.08
    Activations Density 0.002%

    No Known Activations