© 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. 29101
    Prev
    Next
    INDEX
    Explanations

    submit/submission

    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
    гелÑĮ
    -0.08
    å±ĪæĮĩ
    -0.08
    èĢģ人家
    -0.08
    anga
    -0.07
     rabat
    -0.07
    าะ
    -0.07
    äºĨä¸įèµ·
    -0.07
    oyer
    -0.07
    annel
    -0.07
    hani
    -0.07
    POSITIVE LOGITS
     submission
    0.07
    ry
    0.07
     submitted
    0.07
    ä¸İä¹ĭ
    0.07
     submit
    0.07
    Submit
    0.07
    å°ıåŃIJ
    0.07
    èĩªéĢī
    0.07
    submit
    0.06
    submission
    0.06
    Activations Density 0.315%

    No Known Activations