© 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. 43324
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    ÑģÑĤÑĢи
    -0.08
     Preg
    -0.07
    çķħæĥ³
    -0.07
    िला
    -0.07
    elier
    -0.07
    CharCode
    -0.07
    yre
    -0.07
    ellino
    -0.07
    ieder
    -0.07
    tein
    -0.07
    POSITIVE LOGITS
    ë°Ķ
    0.07
    ophon
    0.07
    åīįåİ»
    0.06
    icone
    0.06
    åľ¨æĦı
    0.06
    çīĽçļĦ
    0.06
    ãĤĨ
    0.06
    çīĽ
    0.06
    à±įà°µ
    0.06
    visor
    0.06
    Activations Density 0.176%

    No Known Activations