© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    policy or condition

    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
    ĤŃ
    -0.08
     (!!
    -0.08
    eggi
    -0.08
    ucha
    -0.08
    éĢĹ
    -0.07
    Įĵ
    -0.07
    empla
    -0.07
    {*
    -0.07
    imd
    -0.07
    коÑģ
    -0.07
    POSITIVE LOGITS
    åīį款
    0.11
    æľ¬æ³ķ
    0.09
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.09
    âĢ¦âĢ¦
    0.09
     âĢ¦
    0.08
    ......
    0.08
     [...]
    0.07
     ...
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
     shall
    0.07
    Activations Density 0.033%

    No Known Activations