© 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. 47043
    Prev
    Next
    INDEX
    Explanations

    fraction or division

    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
    ers
    -0.07
    ation
    -0.07
    y
    -0.07
    åŃIJæĽ°
    -0.06
    osis
    -0.06
    Ø©
    -0.06
    ï¸ı
    -0.06
    ument
    -0.06
    sworth
    -0.06
    广åħĥ
    -0.06
    POSITIVE LOGITS
    تÙĨ
    0.08
    ocu
    0.08
    ques
    0.07
    ané
    0.07
    è¾¾æĸ¯
    0.07
    ekar
    0.07
    ËĩËĩ
    0.07
    ucha
    0.07
    sticky
    0.07
     nhau
    0.07
    Activations Density 0.016%

    No Known Activations