© 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. 26077
    Prev
    Next
    INDEX
    Explanations

    star crossed

    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
    åĬ±
    -0.07
    ’T
    -0.07
    ä¸ĭ表
    -0.06
    ש׾
    -0.06
    åĿĩ为
    -0.06
    çłº
    -0.06
    าล
    -0.06
    âĤ¬“
    -0.06
    “
    -0.06
    engi
    -0.06
    POSITIVE LOGITS
     Again
    0.08
     again
    0.08
     appunto
    0.08
    dda
    0.08
     indeed
    0.08
    ä¸įåĸĦ
    0.08
    !.
    0.07
     altså
    0.07
    aroo
    0.07
    ä¸ĩå²ģ
    0.07
    Activations Density 0.156%

    No Known Activations