© 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. 10081
    Prev
    Next
    INDEX
    Explanations

    name or names

    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
    à¸Ļะ
    -0.07
    ιÏĥ
    -0.07
    à¸Ļà¹īำ
    -0.07
    ten
    -0.07
    schritt
    -0.07
    راث
    -0.07
    ij
    -0.07
    imest
    -0.07
     зÑĢениÑı
    -0.07
    à¸Ļà¹īำมัà¸Ļ
    -0.07
    POSITIVE LOGITS
    plate
    0.12
    paced
    0.12
    hood
    0.11
    gebung
    0.11
    geving
    0.11
    plates
    0.10
    lessly
    0.10
    cheap
    0.09
    åĴĮä½ľçĶ¨
    0.09
    ître
    0.09
    Activations Density 0.178%

    No Known Activations