© 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. 28213
    Prev
    Next
    INDEX
    Explanations

    key, serialized, video, code, motion

    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
    åī²
    -0.07
    дви
    -0.07
    egur
    -0.07
    naz
    -0.07
    桦
    -0.06
    ief
    -0.06
    inar
    -0.06
    θÏħν
    -0.06
    æł
    -0.06
    oco
    -0.06
    POSITIVE LOGITS
    agram
    0.09
     clues
    0.08
    åijĪçİ°åľ¨
    0.08
    å¾·æĻº
    0.08
    ÖĦ
    0.08
    åĶ§
    0.07
    人åħ¬
    0.07
     Fron
    0.07
    ldata
    0.07
     clue
    0.07
    Activations Density 0.100%

    No Known Activations