© 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. 29516
    Prev
    Next
    INDEX
    Explanations

    Minecraft or Pokemon

    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
    ellini
    -0.08
    ainter
    -0.07
    ehm
    -0.07
    erein
    -0.07
    ameda
    -0.07
     piv
    -0.07
     intime
    -0.06
     beh
    -0.06
    ROI
    -0.06
    :params
    -0.06
    POSITIVE LOGITS
     Minecraft
    0.08
     Pokémon
    0.08
    ัà¸į
    0.07
    好æĥ³
    0.07
     Wyn
    0.07
    åĽ¾éī´
    0.07
     Cory
    0.07
    çĻĤ
    0.07
     Hogwarts
    0.07
    æľªå¤®
    0.07
    Activations Density 0.076%

    No Known Activations