© 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. 38421
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions or transitions

    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
    cea
    -0.08
    reate
    -0.08
    交æĬķ
    -0.08
     passage
    -0.08
    astre
    -0.08
    velt
    -0.08
    oppins
    -0.08
    èIJ¨çī¹
    -0.08
    ×Ĵר
    -0.08
    oppen
    -0.07
    POSITIVE LOGITS
     buz
    0.07
     hingegen
    0.06
     instead
    0.06
    _symbols
    0.06
     dagegen
    0.06
     invece
    0.06
    amore
    0.06
    amah
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    é©
    0.06
    Activations Density 0.214%

    No Known Activations