© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61659
    Prev
    Next
    INDEX
    Explanations

    conditions used in licenses

    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
     defaultManager
    -0.09
    onomy
    -0.09
    onomies
    -0.09
    Ø©
    -0.08
    quel
    -0.08
    вид
    -0.08
    ยย
    -0.08
    Å¡ÃŃm
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.08
    丼ä¸Ń
    -0.08
    POSITIVE LOGITS
    nement
    0.10
    ality
    0.10
    ãģ¥ãģij
    0.09
    ìĤ¬íķŃ
    0.09
    naires
    0.09
     ìĤ¬íķŃ
    0.08
    sworth
    0.08
    sv
    0.08
    lessly
    0.07
    /method
    0.07
    Activations Density 0.049%

    No Known Activations