© 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. 32229
    Prev
    Next
    INDEX
    Explanations

    1 followed by number or character

    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
    abox
    -0.08
    arate
    -0.08
    forth
    -0.08
    emente
    -0.08
    年代åĪĿ
    -0.07
    raphe
    -0.07
    年代
    -0.07
    fél
    -0.07
    ание
    -0.07
    ients
    -0.07
    POSITIVE LOGITS
    rvine
    0.11
    ambda
    0.10
    ï¸ı
    0.10
    er
    0.09
    st
    0.08
    abeled
    0.08
    äººä¸ºæľ¬
    0.08
    ities
    0.08
    izard
    0.08
    -half
    0.08
    Activations Density 1.493%

    No Known Activations