© 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. 61525
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    imiz
    -0.06
    ival
    -0.06
    ali
    -0.06
    imum
    -0.06
     Earn
    -0.06
    ↵
    -0.06
    ere
    -0.06
    é«ĺåĩº
    -0.06
    ale
    -0.06
    ode
    -0.06
    POSITIVE LOGITS
    itante
    0.08
    ToEnd
    0.08
    aqu
    0.08
    frey
    0.08
    acam
    0.08
     moto
    0.08
    <O
    0.08
    ionalmente
    0.08
     СвеÑĢ
    0.08
    _outputs
    0.08
    Activations Density 0.004%

    No Known Activations