© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    utf-

    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
    bons
    -0.09
    itung
    -0.08
    é¾Ļä¹ĭ
    -0.08
    ories
    -0.08
    קר
    -0.08
    人åĿĩåı¯
    -0.08
    ãĥ¬ãĥĥãĥĪ
    -0.08
    theory
    -0.07
    .ali
    -0.07
    .tex
    -0.07
    POSITIVE LOGITS
     death
    0.07
    opp
    0.06
     enforced
    0.06
    æ½°
    0.06
    è§Ħå®ļçļĦ
    0.06
    æŃ»
    0.06
    æŃ»æ´»
    0.06
     termination
    0.06
    nox
    0.06
    esse
    0.06
    Activations Density 0.001%

    No Known Activations