© 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. 43374
    Prev
    Next
    INDEX
    Explanations

    ceremonies and pre-treatment

    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
    족
    -0.07
    itivas
    -0.07
     appr
    -0.07
    gados
    -0.06
    çļĦæĸ¹æ³ķæĿ¥
    -0.06
    å·¥åķĨæĪ·
    -0.06
    åĩĿç¥ŀ
    -0.06
    ATORS
    -0.06
     Nada
    -0.06
    otos
    -0.06
    POSITIVE LOGITS
    éĵĥ
    0.08
    èµĦæĸĻæĺ¾ç¤º
    0.08
    »
    0.07
    åĨħ容çĶ±
    0.07
    ier
    0.07
    acho
    0.07
    è¡ħ
    0.07
    erra
    0.07
    orm
    0.07
     olarak
    0.07
    Activations Density 0.055%

    No Known Activations