© 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. 13408
    Prev
    Next
    INDEX
    Explanations

    interior point method, boundary conditions, complementarity

    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
    è¿Ķ
    -0.08
    chiere
    -0.08
    neur
    -0.08
    建åĪ¶
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    urin
    -0.08
    ERIC
    -0.08
    VIC
    -0.08
    .Measure
    -0.07
    éĤ¦
    -0.07
    POSITIVE LOGITS
     adherence
    0.07
     complementary
    0.06
    /context
    0.06
    åħ³èģĶ
    0.06
    åĵªäºĽ
    0.06
    åİĭç´§
    0.06
    æ©
    0.06
     activation
    0.06
    Activated
    0.06
     Activation
    0.06
    Activations Density 0.002%

    No Known Activations