© 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. 60967
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    çĶ³æĺİ
    -0.08
    errupt
    -0.07
    .jdbc
    -0.07
     Settembre
    -0.07
    enario
    -0.07
    yman
    -0.07
     BASIS
    -0.07
    ä½ľä¸ºä¸Ģç§į
    -0.07
    .wordpress
    -0.07
    åĽłç¼ĺ
    -0.07
    POSITIVE LOGITS
    彦
    0.07
    iki
    0.07
    odge
    0.06
    æ·¼
    0.06
    缨
    0.06
     ((__
    0.06
    odo
    0.06
    ovas
    0.06
    oter
    0.06
    禺
    0.06
    Activations Density 0.009%

    No Known Activations