© 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. 15602
    Prev
    Next
    INDEX
    Explanations

    HX, OH, ox, ATT, photon

    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
    ÉĻrÉĻ
    -0.07
    thouse
    -0.07
    以å¾ħ
    -0.07
    -_
    -0.06
    /app
    -0.06
    iewicz
    -0.06
    ç¡Ģ
    -0.06
    麻辣çĥ«
    -0.06
    æĢ§è¡Į为
    -0.06
    amber
    -0.06
    POSITIVE LOGITS
    evice
    0.08
    leger
    0.07
    çµĦæĪIJ
    0.07
    é¹ıé£ŀ
    0.07
    åĵĪ
    0.07
    è§Ĥåħī
    0.07
    æIJŃ
    0.07
    ç»ĦæĪIJ
    0.07
    ×ķ׾×Ŀ
    0.06
    åĩºåı°
    0.06
    Activations Density 0.007%

    No Known Activations