© 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. 22079
    Prev
    Next
    INDEX
    Explanations

    Goos-Hänchen shift

    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
    .dist
    -0.08
    çĩİ
    -0.08
    åѤ
    -0.07
    æľĢæĹ©çļĦ
    -0.06
    åĽ´ç»ķ
    -0.06
    _DIS
    -0.06
    éļı
    -0.06
    ç¼Ħ
    -0.06
    çİĩè¾¾åĪ°
    -0.06
    visions
    -0.06
    POSITIVE LOGITS
    /interface
    0.08
    SystemService
    0.08
    éĤ£è¾¹
    0.07
    atatype
    0.07
    æݥ壤
    0.07
    ucr
    0.07
    _greater
    0.07
    ungle
    0.07
    æľªçŁ¥
    0.07
    NIK
    0.07
    Activations Density 0.009%

    No Known Activations