© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    metal complexes

    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
    庸
    -0.06
    忧
    -0.06
    毫
    -0.06
    otten
    -0.06
    toa
    -0.06
    éĴ
    -0.06
    esz
    -0.06
    >j
    -0.06
    vera
    -0.06
     "***
    -0.06
    POSITIVE LOGITS
    inesi
    0.08
    iscos
    0.07
    inium
    0.07
    istischen
    0.07
    iest
    0.07
    ”(
    0.07
    ä¾ĽåºĶä¿¡æģ¯
    0.07
    обÑĢа
    0.07
    StateChanged
    0.07
    riage
    0.07
    Activations Density 0.013%

    No Known Activations