© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    advocacy and related actions

    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
    arily
    -0.07
    haps
    -0.07
    elong
    -0.07
    isable
    -0.07
    iken
    -0.07
    er
    -0.07
    eren
    -0.06
    ath
    -0.06
    erer
    -0.06
    eric
    -0.06
    POSITIVE LOGITS
    ness
    0.17
    ÑģÑı
    0.11
    NESS
    0.11
    ation
    0.10
    Ø©
    0.10
    ãģ¾ãģ¾
    0.09
    ÏĤ
    0.08
    reté
    0.08
    ONGL
    0.08
    erness
    0.08
    Activations Density 0.004%

    No Known Activations