© 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. 42401
    Prev
    Next
    INDEX
    Explanations

    Crunchy, vegetarian recipes

    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
    inga
    -0.09
     ?',
    -0.08
    enhagen
    -0.07
    asil
    -0.07
    %",
    -0.07
    't
    -0.07
    olia
    -0.07
    %',
    -0.07
    iya
    -0.07
    ä»ħæѤ
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
     Âł
    0.07
    reet
    0.07
    utc
    0.07
    ”
    0.07
    asty
    0.07
    ï¸İ
    0.06
    ile
    0.06
    å¦Ĥæŀľåľ¨
    0.06
    lox
    0.06
    Activations Density 0.613%

    No Known Activations