© 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. 24101
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    eben
    -0.08
    oop
    -0.07
    swer
    -0.07
    noj
    -0.06
    nard
    -0.06
    å®Ŀå±±
    -0.06
    benh
    -0.06
    span
    -0.06
     cánh
    -0.06
    Neal
    -0.06
    POSITIVE LOGITS
    ä¸įæ¼ı
    0.08
    ArrayType
    0.08
    ItemSelected
    0.07
    cik
    0.07
    estand
    0.07
    ettino
    0.07
    icl
    0.07
     Alfon
    0.07
    aud
    0.07
    é¡¿äºĨ
    0.07
    Activations Density 0.005%

    No Known Activations