© 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. 60128
    Prev
    Next
    INDEX
    Explanations

    code identifiers and structure

    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
    ×ķ
    -0.08
    ly
    -0.07
    ments
    -0.07
     Meadows
    -0.07
     matters
    -0.07
                        ↵                    ↵
    -0.06
    orÃŃa
    -0.06
    ness
    -0.06
    æľªåĪ°
    -0.06
    ä¸į移
    -0.06
    POSITIVE LOGITS
    ibat
    0.08
    ibri
    0.07
    ForResource
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    apan
    0.07
    kot
    0.07
    äºŃäºŃ
    0.07
    ئا
    0.07
    åīĬ
    0.07
    utta
    0.07
    Activations Density 0.007%

    No Known Activations