© 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. 57022
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    ernote
    -0.08
    æijĬ
    -0.08
    Âł
    -0.07
    æĶ
    -0.07
    ru
    -0.07
    èĥ½ä¸įèĥ½
    -0.07
    _utf
    -0.07
    à¸ĩ
    -0.07
    ,—
    -0.07
    ocks
    -0.06
    POSITIVE LOGITS
     ___
    0.13
     \"
    0.11
    \"
    0.11
     _____
    0.10
    \":
    0.10
    ___
    0.09
     ____
    0.09
    \":\"
    0.09
     '
    0.09
    :\"
    0.09
    Activations Density 0.293%

    No Known Activations