© 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. 64650
    Prev
    Next
    INDEX
    Explanations

    transcription factors

    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
    iator
    -0.09
    iators
    -0.07
    _BITS
    -0.07
    jukan
    -0.07
    ties
    -0.07
    à¸Ľà¸£à¸°à¸ģาร
    -0.07
    ipse
    -0.07
    tó
    -0.07
    ĵĺ
    -0.07
    ithe
    -0.07
    POSITIVE LOGITS
    ric
    0.08
    avanaugh
    0.08
     ulang
    0.08
    ular
    0.08
    uclear
    0.07
    icch
    0.07
    itional
    0.07
    raj
    0.07
    ayar
    0.07
    aub
    0.07
    Activations Density 0.021%

    No Known Activations