© 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. 20620
    Prev
    Next
    INDEX
    Explanations

    yes and question marks

    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±ħçĦ¶
    -0.09
    ç«Ł
    -0.08
    onnen
    -0.07
    å±ħçĦ¶æĺ¯
    -0.07
    ç«ŁçĦ¶
    -0.07
     eens
    -0.07
    åłª
    -0.07
    alist
    -0.07
    æ¼Ĥ
    -0.07
    slag
    -0.06
    POSITIVE LOGITS
     yes
    0.10
    æĺ¯çļĦ
    0.09
     Yes
    0.09
    yes
    0.08
    Yes
    0.08
    å½ĵçĦ¶æĺ¯
    0.08
     YES
    0.08
    ?-
    0.08
    .Yes
    0.08
    æĺ¯åķĬ
    0.07
    Activations Density 0.039%

    No Known Activations