© 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. 32980
    Prev
    Next
    INDEX
    Explanations

    variable assignments after 'b' or 'bar'

    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
    gif
    -0.07
     lour
    -0.07
    kamp
    -0.07
    çĤī
    -0.07
     Ãľbersch
    -0.07
    ersch
    -0.07
    ει
    -0.06
    ssä
    -0.06
    qe
    -0.06
     }>
    -0.06
    POSITIVE LOGITS
    ¢
    0.09
    éric
    0.07
    妮
    0.07
    dux
    0.07
    íݸ
    0.07
    angkal
    0.07
    æĪijä¹Łåİ»
    0.07
    world
    0.06
    ä¸ĸçķĮ大æĪĺ
    0.06
    Ĥ¬
    0.06
    Activations Density 0.046%

    No Known Activations