© 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. 16405
    Prev
    Next
    INDEX
    Explanations

    i.e

    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
     إذÙĨ
    -0.09
    ת×Ļ
    -0.09
    åı¯èĥ½å°±æĺ¯
    -0.08
    ãĥ³ãĥĪãĥ³
    -0.07
     donc
    -0.07
    oque
    -0.07
     Eller
    -0.07
     anyway
    -0.07
    umÄģ
    -0.07
    tesi
    -0.07
    POSITIVE LOGITS
     (!((
    0.10
    omi
    0.07
    æī§è¡Į
    0.07
    ork
    0.07
    asm
    0.06
    ømm
    0.06
    ilib
    0.06
    ipi
    0.06
    ç«Ńè¯ļ
    0.06
    ç¾ļ
    0.06
    Activations Density 0.026%

    No Known Activations