© 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. 23718
    Prev
    Next
    INDEX
    Explanations

    aluminum, Alibaba, Alban

    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
    linger
    -0.08
    ãģĤãĤĮ
    -0.08
    aleigh
    -0.07
    ling
    -0.07
    edList
    -0.07
    .nlm
    -0.07
    linge
    -0.07
    elaar
    -0.07
    er
    -0.07
     Leone
    -0.07
    POSITIVE LOGITS
    buquerque
    0.13
    raries
    0.11
    encontre
    0.11
    istrator
    0.10
    RARY
    0.10
    gorit
    0.10
    fredo
    0.10
    ibrary
    0.10
    iances
    0.10
    igator
    0.10
    Activations Density 0.332%

    No Known Activations