© 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. 2577
    Prev
    Next
    INDEX
    Explanations

    format

    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
    ken
    -0.08
    ä¹ĭæķ°
    -0.07
    rent
    -0.07
    erma
    -0.07
    /remove
    -0.07
    æĬĢæľ¯ä¸Ĭ
    -0.07
    æľ¬èº«
    -0.07
     itself
    -0.07
    ä¹ĭå¤Ħ
    -0.07
    ä¹ĭåīij
    -0.07
    POSITIVE LOGITS
    ou
    0.07
    ิà¹īà¸ĩ
    0.07
    çĺ¾
    0.07
    ÑĪов
    0.07
    undra
    0.07
    lot
    0.07
    :
    0.07
    lots
    0.06
    vod
    0.06
    etrics
    0.06
    Activations Density 0.023%

    No Known Activations