© 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. 30335
    Prev
    Next
    INDEX
    Explanations

    spock.li

    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
    alchemy
    -0.07
    feh
    -0.07
    kaan
    -0.07
    atched
    -0.07
    yle
    -0.07
    ea
    -0.07
     âķ
    -0.06
    å¿ĥåĬ¨
    -0.06
    GENCY
    -0.06
    yla
    -0.06
    POSITIVE LOGITS
    оне
    0.07
    ingan
    0.07
    engel
    0.07
    jump
    0.07
     Cristi
    0.07
    pong
    0.06
     desp
    0.06
    ì·¨
    0.06
    rott
    0.06
     Desp
    0.06
    Activations Density 0.285%

    No Known Activations