© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    rox won

    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
     Almeida
    -0.08
    ä¸įåĢĴ
    -0.07
    banks
    -0.07
     Lazar
    -0.07
    æĪijçĪ±ä½ł
    -0.07
    egative
    -0.07
    ionale
    -0.06
    //----------------------------------------------------------------------------
    -0.06
    å®Įåħ¨çļĦ
    -0.06
    èŁĨ
    -0.06
    POSITIVE LOGITS
    awang
    0.08
    WithValue
    0.08
    noinspection
    0.08
    uko
    0.08
    æĬ¤
    0.07
    datap
    0.07
    è½½
    0.07
    ×Ļר×Ķ
    0.07
    顶å±Ĥ
    0.07
    ay
    0.07
    Activations Density 0.017%

    No Known Activations