© 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. 44982
    Prev
    Next
    INDEX
    Explanations

    common practice / standard method

    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
    ONGO
    -0.08
    alani
    -0.08
    æķ´ä½ĵä¸Ĭ
    -0.07
    entially
    -0.07
    ÙĨاÙĨ
    -0.07
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    -0.07
    gie
    -0.07
    ermen
    -0.07
    波波
    -0.07
    že
    -0.07
    POSITIVE LOGITS
     standards
    0.08
     principles
    0.08
     commonly
    0.08
    /common
    0.07
     terminology
    0.07
    æĥħåĨµè¿Ľè¡Į
    0.07
     conventions
    0.06
    ity
    0.06
    axis
    0.06
    /the
    0.06
    Activations Density 0.010%

    No Known Activations