© 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. 63434
    Prev
    Next
    INDEX
    Explanations

    field

    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
    θÏħ
    -0.07
    åįĬéĢĶ
    -0.07
    å¢ħ
    -0.07
    åįķæĸ¹éĿ¢
    -0.07
    ignes
    -0.07
    zis
    -0.06
    ysz
    -0.06
    éĥ´
    -0.06
    igy
    -0.06
    AX
    -0.06
    POSITIVE LOGITS
     insp
    0.07
    pek
    0.07
    æ¸Ī
    0.07
     Caval
    0.06
    ëį©
    0.06
     flavours
    0.06
     colours
    0.06
    活水
    0.06
    Pooling
    0.06
    olla
    0.06
    Activations Density 0.015%

    No Known Activations