© 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. 10339
    Prev
    Next
    INDEX
    Explanations

    epic, vast, majestic, expansive

    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
     domicili
    -0.08
    çİĩä½İ
    -0.08
    æľīåij³
    -0.08
    踪影
    -0.08
    è¾ĥè½»
    -0.08
    ä¹ĸå·§
    -0.08
    éĿĴ涩
    -0.07
    Spot
    -0.07
    arest
    -0.07
    ecke
    -0.07
    POSITIVE LOGITS
    ç£ħ礴
    0.14
    壮è§Ĥ
    0.13
    æ°ĶåĬ¿
    0.13
    壮éĺĶ
    0.13
    çļĦæ°ĶåĬ¿
    0.12
    èĥ¸æĢĢ
    0.12
    壮丽
    0.12
    panse
    0.11
    浩
    0.11
     expansive
    0.11
    Activations Density 0.091%

    No Known Activations