© 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. 39221
    Prev
    Next
    INDEX
    Explanations

    Author, Also, Out, Tuesday, Indian, From, This

    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
    mend
    -0.07
    ossi
    -0.07
    issé
    -0.07
    åľ¨èIJ¥
    -0.07
    asar
    -0.07
    欢è¿İæĤ¨çļĦ
    -0.07
    áĪŃ
    -0.07
    éŁ
    -0.07
    istring
    -0.07
    awat
    -0.07
    POSITIVE LOGITS
    arca
    0.08
    ontan
    0.08
    çī¹çĤ¹æĺ¯
    0.07
    æ·¡æ·¡çļĦ
    0.07
    ains
    0.07
    Ģ
    0.06
    _DLL
    0.06
    `=
    0.06
    @@
    0.06
    =f
    0.06
    Activations Density 0.011%

    No Known Activations