© 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. 55446
    Prev
    Next
    INDEX
    Explanations

    two items

    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
    ParseException
    -0.08
    æł¼éĩĮ
    -0.08
    ä¸ĥéĩĮ
    -0.08
    äºĮ代
    -0.08
    åĩłå¼ł
    -0.08
     succesfully
    -0.07
    ocache
    -0.07
    åĩłå£°
    -0.07
    vice
    -0.07
    egen
    -0.07
    POSITIVE LOGITS
    —one
    0.19
    ä¸Ģ个æĺ¯
    0.12
     íķĺëĤĺëĬĶ
    0.11
    ä¸Ģæĺ¯
    0.11
     biri
    0.10
    —the
    0.10
    —from
    0.10
    åħ¶ä¸Ń
    0.10
    ä¸Ģç§įæĺ¯
    0.10
    ——
    0.09
    Activations Density 0.189%

    No Known Activations