© 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. 23308
    Prev
    Next
    INDEX
    Explanations

    technical code and programming

    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
    inue
    -0.07
    oto
    -0.06
     hum
    -0.06
    eldes
    -0.06
    ä½ķåħ¶
    -0.06
    ast
    -0.06
     Blanc
    -0.06
    <|fim_prefix|>
    -0.06
     novel
    -0.06
    legation
    -0.06
    POSITIVE LOGITS
    اسب
    0.08
    -friendly
    0.08
    èĿ¶
    0.08
    -extra
    0.08
     dita
    0.08
    razier
    0.07
    å¦į
    0.07
    Scalars
    0.07
    ubb
    0.07
    ron
    0.07
    Activations Density 0.001%

    No Known Activations