© 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. 25632
    Prev
    Next
    INDEX
    Explanations

    omega, n, R, C, γ

    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
    elen
    -0.07
    转贴
    -0.07
    .flags
    -0.07
    ÙĨدÙĩ
    -0.07
    å½ĵéĢī
    -0.07
    flags
    -0.07
    chet
    -0.06
     اÙĦÙħسÙĦÙħ
    -0.06
    çĮĸ
    -0.06
    ÙĪز
    -0.06
    POSITIVE LOGITS
    arendra
    0.09
    ä¸Ģæĸ°
    0.08
    æĪijçļĦ人
    0.07
    æµ®äºij
    0.07
    ifferent
    0.07
    ì¶Ķ
    0.07
    好人
    0.07
    epsi
    0.06
    isca
    0.06
    arsed
    0.06
    Activations Density 0.005%

    No Known Activations