© 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. 17123
    Prev
    Next
    INDEX
    Explanations

    text formatting

    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
    segue
    -0.09
    udir
    -0.09
    尼奥
    -0.09
    ızı
    -0.09
    íħĶ
    -0.09
    åºĶæīĭ
    -0.09
    avera
    -0.09
    OVO
    -0.09
    veau
    -0.09
    оÑģÑĤа
    -0.08
    POSITIVE LOGITS
    text
    0.08
    ี
    0.07
    ed
    0.07
     The
    0.06
    thumb
    0.06
    0.06
    ej
    0.06
    oriously
    0.06
    it
    0.06
    amment
    0.06
    Activations Density 0.031%

    No Known Activations