© 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. 12852
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    æĽ³
    -0.09
    dete
    -0.08
    zne
    -0.07
    érance
    -0.07
    èĤĭ骨
    -0.07
     Merke
    -0.07
    ç½ijç«Ļ导èĪª
    -0.07
    obiet
    -0.07
    iteln
    -0.07
    /DD
    -0.07
    POSITIVE LOGITS
    ä¹İ
    0.08
    æŀĿ
    0.07
    elif
    0.07
    äºİä¸Ģ
    0.07
    äºİè¡Į
    0.07
    ella
    0.07
    aly
    0.07
    åIJİæīį
    0.07
    igy
    0.07
    åı¦
    0.07
    Activations Density 0.008%

    No Known Activations