© 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. 56530
    Prev
    Next
    INDEX
    Explanations

    whether it is

    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
    cape
    -0.07
    èĢĥ
    -0.07
     Especially
    -0.07
    å°¤åħ¶æĺ¯
    -0.06
    ä¸įåıĬ
    -0.06
    ape
    -0.06
    uch
    -0.06
    ìn
    -0.06
    aptor
    -0.06
    енÑĮе
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¸Ģå®ļ
    0.09
     tampoco
    0.08
    ãģĿãĤĤãģĿãĤĤ
    0.08
    IGO
    0.08
    nore
    0.07
    erse
    0.07
    >')
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    ingan
    0.07
     "==
    0.07
    Activations Density 0.302%

    No Known Activations