© 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. 4115
    Prev
    Next
    INDEX
    Explanations

    Southern Motors

    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
    æĭŃ缮
    -0.07
    odik
    -0.06
    bsites
    -0.06
    lob
    -0.06
    åIJĪä½ľçĶ¨
    -0.06
    ossi
    -0.06
    onomy
    -0.06
    ë
    -0.06
    æŶæĹł
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
    ilan
    0.07
    üste
    0.07
    çĴĢ
    0.07
    PageIndex
    0.07
    ciano
    0.06
    çĸĻ
    0.06
     Flake
    0.06
    endÅij
    0.06
    ungan
    0.06
     kef
    0.06
    Activations Density 0.091%

    No Known Activations