© 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. 61167
    Prev
    Next
    INDEX
    Explanations

    department/section titles

    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
    &w
    -0.09
    hoven
    -0.09
    inari
    -0.09
     prosp
    -0.08
    quine
    -0.08
    å®Ĺ亲
    -0.08
    eteg
    -0.08
    Úĺ
    -0.08
    èĩªå·±çļĦ人
    -0.08
    -driver
    -0.08
    POSITIVE LOGITS
    Âł
    0.07
    åıĹåĪ°äºĨ
    0.06
    it
    0.06
    {
    0.06
    enton
    0.06
    awal
    0.06
    çīµ
    0.06
    -
    0.06
     Render
    0.05
    稽
    0.05
    Activations Density 0.147%

    No Known Activations