© 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. 37845
    Prev
    Next
    INDEX
    Explanations

    resources, influence, fifth, fluids

    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
    uff
    -0.07
    xEF
    -0.07
    vej
    -0.06
    ited
    -0.06
    桦
    -0.06
     Hilton
    -0.06
    åĽĽå¤Ħ
    -0.06
    itive
    -0.06
    aroo
    -0.06
    æĹłå¿Į
    -0.05
    POSITIVE LOGITS
    æĢ§åĬŁèĥ½
    0.08
    umbu
    0.07
    rotch
    0.07
    isnan
    0.07
    æĹ¥èµ·èĩ³
    0.07
    narod
    0.07
    odo
    0.07
    employ
    0.07
    alam
    0.07
    гÑĢе
    0.07
    Activations Density 0.361%

    No Known Activations