© 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. 65332
    Prev
    Next
    INDEX
    Explanations

    followed by to

    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
     isbn
    -0.07
    orden
    -0.07
     (âĢ¦)
    -0.06
    ±ħ
    -0.06
    ä¸į顺
    -0.06
    ugat
    -0.06
    êµīìŀ¥
    -0.06
    .IsNotNull
    -0.06
    꽤
    -0.06
    ULE
    -0.06
    POSITIVE LOGITS
    APPER
    0.08
    aner
    0.07
    èĪ¶
    0.07
    çİ«
    0.07
    ä¹Ī
    0.07
    otos
    0.07
    ä¹ĥ
    0.07
    onn
    0.07
    aka
    0.06
    ç¥IJ
    0.06
    Activations Density 5.820%

    No Known Activations