© 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. 20190
    Prev
    Next
    INDEX
    Explanations

    username or name fields

    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
    à¸ľà¹Īà¸Ńà¸Ļ
    -0.07
    åį°
    -0.07
    aal
    -0.07
    ×ķרת
    -0.07
    èµ°
    -0.07
    磨
    -0.06
    è¿ĺæĺ¯åľ¨
    -0.06
     خص
    -0.06
     reimb
    -0.06
    踪
    -0.06
    POSITIVE LOGITS
    /navbar
    0.08
    acher
    0.08
    æľªæĿ¥åıijå±ķ
    0.07
    UNCH
    0.07
    çļĦæĢĿèĢĥ
    0.07
    cius
    0.07
     Monter
    0.07
    èī¯
    0.07
    _FL
    0.06
    é£Ļ
    0.06
    Activations Density 0.213%

    No Known Activations