© 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. 50130
    Prev
    Next
    INDEX
    Explanations

    web links and addresses

    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
    'Connor
    -0.07
    vertime
    -0.07
    ILED
    -0.07
    ekh
    -0.07
    Ĺ
    -0.07
    lymp
    -0.07
    plevel
    -0.07
    engel
    -0.07
    ähl
    -0.07
    inkin
    -0.07
    POSITIVE LOGITS
    ages
    0.12
    edly
    0.12
    ed
    0.09
    ungan
    0.09
     nhau
    0.09
    ings
    0.09
    sWith
    0.09
    iewicz
    0.09
    纽带
    0.09
    ä¸įçķħ
    0.09
    Activations Density 0.056%

    No Known Activations