© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    roman numerals (i, ii, iii, iv, v, vi, viii)

    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
    edException
    -0.08
    ingly
    -0.08
    nable
    -0.08
    ecurity
    -0.07
    itude
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    esh
    -0.07
     vặt
    -0.07
    ness
    -0.07
    beit
    -0.07
    POSITIVE LOGITS
    ancock
    0.08
    °
    0.07
    iterate
    0.07
    ories
    0.07
    ÙĪاÙĦ
    0.07
    aries
    0.07
     Jinping
    0.07
    олÑĮ
    0.07
    -thirds
    0.07
    bons
    0.07
    Activations Density 0.049%

    No Known Activations