© 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. 50401
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    ebbe
    -0.06
     *(*
    -0.06
    aton
    -0.06
    .cf
    -0.06
    몽
    -0.06
    ivet
    -0.06
    idge
    -0.06
    eba
    -0.06
    اÙħت
    -0.06
    å¼ı
    -0.06
    POSITIVE LOGITS
    uas
    0.08
    ÑģаÑĢ
    0.08
    oston
    0.08
    _None
    0.07
    åİĨ
    0.07
    ä½łåij¢
    0.07
    以å¤ĩ
    0.07
    inel
    0.07
    (()=>
    0.07
    kost
    0.07
    Activations Density 0.002%

    No Known Activations