© 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. 40943
    Prev
    Next
    INDEX
    Explanations

    AB peptide

    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
    翼翼
    -0.09
    sburg
    -0.08
    heits
    -0.08
    ystal
    -0.08
    æ²³éĩĮ
    -0.08
    umpang
    -0.08
    ussen
    -0.08
    ÙĪÙĦÙĬÙĨ
    -0.08
     latter
    -0.07
    åIJİåį³
    -0.07
    POSITIVE LOGITS
    encontre
    0.09
    ัà¸ĩ
    0.08
    ection
    0.08
    ination
    0.08
    shire
    0.08
    w
    0.08
    auce
    0.07
    relude
    0.07
    εί
    0.07
    ees
    0.07
    Activations Density 0.027%

    No Known Activations