© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17620
    Prev
    Next
    INDEX
    Explanations

    distribution of

    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
    æĥħæĦı
    -0.07
    nex
    -0.07
    gart
    -0.07
    cev
    -0.07
    è¡ĮéĹ´
    -0.07
     casser
    -0.07
    åĬ
    -0.07
    enhagen
    -0.06
    (||
    -0.06
    æĸŃå¼Ģ
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.15
     distribution
    0.15
     distributions
    0.15
    distribution
    0.14
     Distribution
    0.13
    Distribution
    0.12
     distribución
    0.12
    istribution
    0.12
     distribuição
    0.12
     ÑĢаÑģпÑĢе
    0.11
    Activations Density 0.024%

    No Known Activations