© 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. 24765
    Prev
    Next
    INDEX
    Explanations

    parts and their components

    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
    uhan
    -0.09
    ural
    -0.08
    æĪĸå¤ļ个
    -0.08
    avel
    -0.07
    uran
    -0.07
    urally
    -0.07
    icky
    -0.07
    æĹ¥çĶŁ
    -0.06
    è¿ĩåħ³
    -0.06
    Pipeline
    -0.06
    POSITIVE LOGITS
    ivid
    0.07
    éĤªéŃĶ
    0.07
     propre
    0.07
    éĢĻä¸Ģ
    0.07
    меÑĤа
    0.06
    qq
    0.06
    fond
    0.06
    Metadata
    0.06
    ê²łëĭ¤ëĬĶ
    0.06
    embedded
    0.06
    Activations Density 0.250%

    No Known Activations