© 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. 18915
    Prev
    Next
    INDEX
    Explanations

    explanation / explanations

    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
    æĽ´åIJį
    -0.07
    esten
    -0.07
    åħįè´¹åĴ¨è¯¢
    -0.07
    zyw
    -0.06
    ordat
    -0.06
    çĥŃéŨæĸĩç«ł
    -0.06
    _apps
    -0.06
    uestion
    -0.06
    åIJİæľī
    -0.06
    εÏħ
    -0.06
    POSITIVE LOGITS
    åİĨåİĨ
    0.09
    å¢ħ
    0.08
    atorio
    0.08
     explanations
    0.08
     dévo
    0.07
    åĿĬ
    0.07
    æŀ¯çĩ¥
    0.07
    åIJĮè¡Į
    0.07
     explanation
    0.07
    Explanation
    0.07
    Activations Density 0.016%

    No Known Activations