© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46629
    Prev
    Next
    INDEX
    Explanations

    letters and numbers

    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
    ç½ijéĢļ
    -0.07
     ëĤĺ
    -0.07
    _back
    -0.07
     Crow
    -0.07
    ØŃاء
    -0.06
    å·´å°Ķ
    -0.06
    ren
    -0.06
     Pastor
    -0.06
    _tokenize
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
    utton
    0.09
    venta
    0.08
    íķ©
    0.08
     input
    0.07
    alai
    0.07
    oline
    0.07
    声åĬ¿
    0.07
    缸å¾ĹçĽĬå½°
    0.07
     versus
    0.07
    ת
    0.07
    Activations Density 0.042%

    No Known Activations