© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    view immediately, code that, ones that

    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
    å·¥ä½ľåıĬ
    -0.08
    ungg
    -0.07
    Insensitive
    -0.07
    arih
    -0.07
    mdb
    -0.06
    _negative
    -0.06
    åħĥèµ·
    -0.06
    åıĸå¾Ĺæĸ°
    -0.06
    vergleich
    -0.06
    adia
    -0.06
    POSITIVE LOGITS
     rather
    0.10
     plutôt
    0.10
    èĢĮä¸įæĺ¯
    0.09
    rather
    0.09
    èĢĮéĿŀ
    0.08
     Rather
    0.08
     ÙģØŃسب
    0.08
     лиÑĪÑĮ
    0.07
    ä¹Łåıªæĺ¯
    0.07
    åıªæĺ¯ä¸Ģ
    0.07
    Activations Density 0.421%

    No Known Activations