© 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. 51395
    Prev
    Next
    INDEX
    Explanations

    PUNCTUATION AND ABBREVIATIONS

    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
    /ext
    -0.08
    erio
    -0.07
    _TRY
    -0.07
    ?url
    -0.07
    orrow
    -0.07
    _ATTACH
    -0.07
    rek
    -0.07
    :host
    -0.07
    onex
    -0.07
    ever
    -0.07
    POSITIVE LOGITS
    çIJĨçļĦ
    0.07
    åı¯è¡Į
    0.07
    odes
    0.07
    hto
    0.07
     terci
    0.06
    ÙĪرات
    0.06
    perm
    0.06
    è¡Įèĩ³
    0.06
    TRS
    0.06
     viola
    0.06
    Activations Density 0.012%

    No Known Activations