© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21794
    Prev
    Next
    INDEX
    Explanations

    rotated

    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
    utel
    -0.08
    oris
    -0.07
    ãĥĥãĤ«
    -0.07
    为ä¸Ĭ
    -0.07
    代ãĤıãĤĬãģ«
    -0.07
    aina
    -0.07
     волнÑĥ
    -0.07
    æİĴ忧解éļ¾
    -0.07
    水泡
    -0.07
    该çīĩ
    -0.07
    POSITIVE LOGITS
    ellar
    0.07
    ihak
    0.07
    arty
    0.07
    äºĨ解ä¸Ģä¸ĭ
    0.07
    ÅŁehir
    0.07
    stry
    0.06
    以å¾ħ
    0.06
     Chall
    0.06
    arsing
    0.06
    à¸Ľà¸±à¸Ļ
    0.06
    Activations Density 0.007%

    No Known Activations