© 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. 30394
    Prev
    Next
    INDEX
    Explanations

    Petrov, valentine, Kim

    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
     frustra
    -0.09
    åIJijèį£
    -0.09
     Chauss
    -0.08
    issons
    -0.08
    å®ļäºĨ
    -0.08
     [<
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    .mods
    -0.08
     acá
    -0.08
    iesta
    -0.08
    POSITIVE LOGITS
     K
    0.07
     C
    0.07
    ä¸įæ²»
    0.07
     F
    0.06
    io
    0.06
    K
    0.06
     O
    0.06
     dos
    0.06
    Core
    0.06
    éĨĴ
    0.06
    Activations Density 0.784%

    No Known Activations