© 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. 24060
    Prev
    Next
    INDEX
    Explanations

    chief factor

    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
    ignet
    -0.08
    offset
    -0.07
    ody
    -0.07
    annis
    -0.07
     ÙħØ°
    -0.07
    angat
    -0.07
    asan
    -0.07
    inous
    -0.07
    QU
    -0.07
    äss
    -0.07
    POSITIVE LOGITS
    ä¸įèĥ½åĨį
    0.10
    enu
    0.08
    kamp
    0.07
    åĨįä¹Łæ²¡æľī
    0.07
     uniqueness
    0.07
    ingleton
    0.07
    级çļĦ
    0.07
    åºĬè¾¹
    0.07
    大éĩij
    0.07
     minim
    0.07
    Activations Density 0.008%

    No Known Activations