© 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. 13255
    Prev
    Next
    INDEX
    Explanations

    ms followed by .prod or .date

    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
    Ñģполни
    -0.10
    .openg
    -0.09
    -License
    -0.09
    rados
    -0.09
    aéroport
    -0.08
     coquine
    -0.08
    ernals
    -0.08
    gup
    -0.08
    ugins
    -0.08
    ÙĨاÙħÙĩ
    -0.08
    POSITIVE LOGITS
    âĢ¢
    0.06
    èĢĮæŃ»
    0.06
    ent
    0.06
    æ¸ħ
    0.05
    2
    0.05
    ivant
    0.05
    ·
    0.05
    terer
    0.05
    urr
    0.05
    ol
    0.05
    Activations Density 0.011%

    No Known Activations