© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    archaeal

    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
     доÑģ
    -0.07
    रण
    -0.07
    èī¯
    -0.07
     Bris
    -0.07
    èľ»
    -0.07
    odem
    -0.07
    åĨ³å®ļçļĦ
    -0.06
    _flutter
    -0.06
    bÄĽ
    -0.06
    æ¡Ķ
    -0.06
    POSITIVE LOGITS
    深海
    0.09
     microbial
    0.09
     Antarctic
    0.08
    çĶŁçī©
    0.08
    å¾®çĶŁçī©
    0.08
     bio
    0.08
    explo
    0.08
    èıĮ群
    0.08
    åĭĺæİ¢
    0.08
     bacteria
    0.08
    Activations Density 0.054%

    No Known Activations