© 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. 29290
    Prev
    Next
    INDEX
    Explanations

    variable assignments with `+` or `-`

    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
    gal
    -0.07
    uvi
    -0.07
    fo
    -0.06
    人åĪ°
    -0.06
    vid
    -0.06
    rijk
    -0.06
     gal
    -0.06
    绪
    -0.06
     sembl
    -0.06
    za
    -0.06
    POSITIVE LOGITS
    olls
    0.08
    ecat
    0.07
     minus
    0.07
     Auc
    0.07
    ancy
    0.07
    ioneer
    0.07
    minus
    0.07
    owie
    0.07
    oppins
    0.07
    reation
    0.07
    Activations Density 0.004%

    No Known Activations