© 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. 60363
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    اÙĭ
    -0.14
    ially
    -0.12
    raries
    -0.12
    èĩªå·±
    -0.11
    ezo
    -0.10
    maÃŁen
    -0.10
    หมาย
    -0.10
    èĩªå·±è¢«
    -0.10
    ly
    -0.10
    اÙĥ
    -0.10
    POSITIVE LOGITS
    Ø©
    0.19
    i
    0.11
    vironment
    0.10
    ãģĦãĤĭ
    0.10
    ness
    0.09
    s
    0.09
    entication
    0.08
    ar
    0.08
    ÙĪÙĦØ©
    0.08
    ation
    0.08
    Activations Density 0.047%

    No Known Activations