© 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. 60379
    Prev
    Next
    INDEX
    Explanations

    current IP address or directory

    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
    ffel
    -0.09
    çĪ¶å¥³
    -0.09
    unda
    -0.08
    okes
    -0.08
    .createClass
    -0.08
    handleRequest
    -0.08
    raga
    -0.08
    æī¬èµ·
    -0.08
    rowse
    -0.08
    createForm
    -0.08
    POSITIVE LOGITS
    èİ·åıĸ
    0.09
     GetCurrent
    0.08
     current
    0.08
    .getCurrent
    0.07
    å¤§æľ¬
    0.07
     Current
    0.07
    Current
    0.07
    å¿«éĢŁèİ·åıĸ
    0.07
    æĿ¥èİ·åıĸ
    0.07
    èĩªçľģ
    0.07
    Activations Density 0.585%

    No Known Activations