© 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. 21542
    Prev
    Next
    INDEX
    Explanations

    . followed by capital letter

    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
    /or
    -0.07
    izard
    -0.07
    å¿ĺè®°
    -0.07
     ********************************************************
    -0.06
    èµ·
    -0.06
    irs
    -0.06
     hers
    -0.06
    azel
    -0.06
    ower
    -0.06
    efeld
    -0.06
    POSITIVE LOGITS
    anser
    0.07
    ìĽĮìĦľ
    0.07
    /vendors
    0.07
    ophysical
    0.07
    _keyword
    0.07
    妥
    0.07
    omens
    0.07
    ksam
    0.07
    cents
    0.07
    /tab
    0.07
    Activations Density 0.001%

    No Known Activations