© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    gradual reduction or steps

    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
    alars
    -0.07
    éĻ¨èIJ½
    -0.07
    неÑĨ
    -0.07
    ocode
    -0.07
    Ñģно
    -0.07
    oros
    -0.07
    åĿ¤
    -0.06
    ÐŀÐĿ
    -0.06
     CY
    -0.06
    æĽ´æŃ£
    -0.06
    POSITIVE LOGITS
     gradually
    0.18
    éĢIJæŃ¥
    0.16
     gradual
    0.16
    éĢIJæ¸IJ
    0.15
     Grad
    0.14
     تدرÙĬ
    0.14
    grad
    0.14
    Grad
    0.13
     поÑģÑĤепенно
    0.13
    æħ¢æħ¢
    0.13
    Activations Density 0.111%

    No Known Activations