© 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. 2408
    Prev
    Next
    INDEX
    Explanations

    re-evaluation or check again

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    SDL
    -0.06
     pil
    -0.06
    kul
    -0.06
    inning
    -0.06
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    arte
    -0.06
     åt
    -0.06
     либо
    -0.06
    -
    -0.05
    POSITIVE LOGITS
    ä¸Ģéģį
    0.11
    äºĨä¸Ģéģį
    0.10
    Than
    0.09
     THAN
    0.09
    abeth
    0.09
    wards
    0.08
    æĬķåħ¥åĪ°
    0.08
    ÑĤаки
    0.08
    than
    0.08
    assi
    0.08
    Activations Density 0.007%

    No Known Activations