© 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. 31727
    Prev
    Next
    INDEX
    Explanations

    expand or collapse

    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
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.08
     rem
    -0.07
    ÑĢоб
    -0.06
    вÑĢа
    -0.06
    оÑĢов
    -0.06
    Birthday
    -0.06
    ground
    -0.06
    HTTPRequest
    -0.06
    аÑĤаÑĢ
    -0.06
    Hotline
    -0.06
    POSITIVE LOGITS
    å±ķå¼Ģ
    0.11
    opened
    0.11
    -hidden
    0.10
    æīĵå¼Ģ
    0.10
    èĹı
    0.10
    éļIJèĹı
    0.10
     hidden
    0.10
     concealed
    0.10
    :hidden
    0.10
    -collapse
    0.10
    Activations Density 0.150%

    No Known Activations