© 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. 58092
    Prev
    Next
    INDEX
    Explanations

    On Monday

    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
    ariato
    -0.08
    æĹ©çĤ¹
    -0.08
    istro
    -0.08
    linky
    -0.08
     Yugosl
    -0.08
    -Za
    -0.08
    ossier
    -0.08
    -trash
    -0.08
    ynamo
    -0.08
    å®īéĺ³
    -0.08
    POSITIVE LOGITS
     armour
    0.07
    åij¨æĿ°
    0.06
    çŃł
    0.06
    {
    0.06
     favourite
    0.05
    ÑĪÑijл
    0.05
     mould
    0.05
     акÑĥ
    0.05
    æ³ĵ
    0.05
    Tick
    0.05
    Activations Density 0.185%

    No Known Activations