© 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. 13057
    Prev
    Next
    INDEX
    Explanations

    numeric characters and punctuation

    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
    MSN
    -0.07
    isphere
    -0.07
    åĴĮåIJĮåѦ
    -0.07
    irat
    -0.07
    alami
    -0.07
    вай
    -0.07
    antos
    -0.07
    COPE
    -0.07
    erior
    -0.07
    fade
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸īç§į
    0.08
    è¢ħè¢ħ
    0.07
    ëķħ
    0.06
    çĨı
    0.06
    çī¹å®ļçļĦ
    0.06
    urre
    0.06
    ouro
    0.06
    illet
    0.06
    åĬ©
    0.06
    çī¹å®ļ
    0.06
    Activations Density 0.021%

    No Known Activations