© 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. 1708
    Prev
    Next
    INDEX
    Explanations

    positive numbers, math equations

    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
    æıĥ
    -0.08
    å¾Īå¤ļåľ°æĸ¹
    -0.08
    à´°àµģ
    -0.08
     prét
    -0.07
    ãģĿãĤį
    -0.07
    uerta
    -0.07
    eming
    -0.07
    åļ£
    -0.07
    вÑĢемен
    -0.07
    æī¬éķ¿
    -0.07
    POSITIVE LOGITS
     positive
    0.12
     Positive
    0.12
    èĤ¯å®ļ
    0.11
     positivity
    0.11
    -positive
    0.11
    Positive
    0.10
    èĤ¯å®ļæĺ¯
    0.10
     positively
    0.10
    positive
    0.10
    æ°¸è¿ľ
    0.10
    Activations Density 0.022%

    No Known Activations