© 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. 42666
    Prev
    Next
    INDEX
    Explanations

    Bakal

    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
    oses
    -0.07
    eges
    -0.07
    ¥
    -0.07
    à¥į
    -0.07
    ære
    -0.07
    |min
    -0.07
    deo
    -0.07
    ogna
    -0.06
    ¢
    -0.06
    uries
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įè§ģ
    0.07
    akk
    0.07
    isu
    0.07
     Bakal
    0.07
    çĤ¹èĩ³
    0.07
    ç´¢
    0.07
    ak
    0.07
    è¡£èįī
    0.06
    ikai
    0.06
    ç¬ijçĿĢ说éģĵ
    0.06
    Activations Density 0.010%

    No Known Activations