© 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. 15822
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, integral, bounding

    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
    åħĭæĭī
    -0.06
    åĪ
    -0.06
    agrid
    -0.06
    为æķ°
    -0.06
    anen
    -0.06
    uken
    -0.06
    akit
    -0.06
    æĺ¾èijĹ
    -0.06
    é²ľ
    -0.06
    _scale
    -0.06
    POSITIVE LOGITS
    ä¸įè¶ħè¿ĩ
    0.10
    ä½Ĩèĩ³å°ij
    0.10
     âī¤
    0.10
    Bounding
    0.09
    èĩ³å°ijæľī
    0.09
    ä¸į大äºİ
    0.09
     Bounds
    0.09
     Bound
    0.09
     bounds
    0.09
    ä¸įä½İäºİ
    0.09
    Activations Density 0.011%

    No Known Activations