© 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. 62020
    Prev
    Next
    INDEX
    Explanations

    html id attributes

    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
     меÑħани
    -0.07
    ä¹īè¯į
    -0.07
    سÙĦاÙħ
    -0.07
    ifat
    -0.07
    AVE
    -0.07
    INET
    -0.07
    æĻ®ç½Ĺ
    -0.06
    ä¸įåĩºæĿ¥
    -0.06
    war
    -0.06
    ALSE
    -0.06
    POSITIVE LOGITS
    bens
    0.07
    æīĢéľĢè¦ģ
    0.07
    æĺĬ天
    0.07
    áÄį
    0.06
    øl
    0.06
    hoto
    0.06
    ampo
    0.06
    èĩ³å°ij
    0.06
     processes
    0.06
    reo
    0.06
    Activations Density 0.046%

    No Known Activations