© 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. 31473
    Prev
    Next
    INDEX
    Explanations

    remediation, reconstruction, measurement, vector, treatment, evidence, powered electrical, detector system

    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
    æĪĪå°Ķ
    -0.09
    ÑĨиона
    -0.08
    éĵģè¡Ģ
    -0.08
    åīįèĮħ
    -0.08
    è¢«ä½ł
    -0.08
     bấy
    -0.07
    ä¹IJä¹İ
    -0.07
    EGI
    -0.07
    umble
    -0.07
    estina
    -0.07
    POSITIVE LOGITS
    нг
    0.06
     versus
    0.06
    解éļ¾
    0.06
     Ep
    0.06
    itable
    0.06
     ìĿĺíķľ
    0.06
    aph
    0.06
    æ³ķ
    0.06
    anei
    0.06
     vs
    0.06
    Activations Density 0.664%

    No Known Activations