© 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. 49341
    Prev
    Next
    INDEX
    Explanations

    questions and beginnings of phrases

    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
    让è¿Ļ个
    -0.07
    è§ģæѤ
    -0.07
    对æѤ
    -0.07
    ogan
    -0.07
    ses
    -0.07
    agher
    -0.07
    è°£
    -0.06
    olum
    -0.06
    失çģµ
    -0.06
    еÑģÑĮ
    -0.06
    POSITIVE LOGITS
    ibox
    0.08
    wiad
    0.08
    _within
    0.08
    mlink
    0.07
    Typed
    0.07
     puntu
    0.07
    "';
    0.07
    ToDelete
    0.07
    plash
    0.07
     Weiner
    0.07
    Activations Density 0.010%

    No Known Activations