© 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. 57344
    Prev
    Next
    INDEX
    Explanations

    mathematical statements and definitions

    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
    ropp
    -0.08
    eaux
    -0.07
    Neill
    -0.07
    åIJİåį³
    -0.07
    åį¡è¥¿
    -0.07
    .sf
    -0.07
    veau
    -0.07
    ç»Ļ对æĸ¹
    -0.07
    olon
    -0.07
    apesh
    -0.07
    POSITIVE LOGITS
    त
    0.07
    ä¾Ī
    0.07
    éĤ£ä¹Ī
    0.07
    以ä¸ĭæĿ¡ä»¶
    0.06
    theit
    0.06
     acond
    0.06
     every
    0.06
    ¬
    0.06
    å°
    0.06
    ç¿ĺ
    0.06
    Activations Density 0.012%

    No Known Activations