© 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. 33537
    Prev
    Next
    INDEX
    Explanations

    vector magnitudes

    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
    Õ¡Õ°
    -0.08
    פ׾
    -0.08
    klink
    -0.07
    alc
    -0.07
    çģ¾æĥħ
    -0.07
    åľ¨åģļ好
    -0.07
    Õ¡Õ½
    -0.07
    _MAPPING
    -0.07
    incid
    -0.07
    pter
    -0.07
    POSITIVE LOGITS
    -vector
    0.08
     CGSize
    0.08
     squared
    0.08
    æĺ±
    0.08
    uster
    0.07
     vectors
    0.07
     Wester
    0.07
     Vector
    0.07
    Vector
    0.07
     vector
    0.07
    Activations Density 0.007%

    No Known Activations