© 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. 31486
    Prev
    Next
    INDEX
    Explanations

    I was / guy was

    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
     support
    -0.06
    CM
    -0.06
    ustain
    -0.06
     Aks
    -0.06
    ardown
    -0.06
    æĥ
    -0.06
    æ½®
    -0.06
    å´İ
    -0.06
     formul
    -0.06
     Support
    -0.06
    POSITIVE LOGITS
    ayan
    0.09
    ивно
    0.08
    illusion
    0.08
    trom
    0.08
    اÙĥ
    0.07
    rani
    0.07
    jan
    0.07
    ayne
    0.07
    aro
    0.07
    edo
    0.07
    Activations Density 0.198%

    No Known Activations