© 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. 28500
    Prev
    Next
    INDEX
    Explanations

    Pokemon Black

    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
    çĽ²
    -0.07
     "}
    -0.07
    illen
    -0.06
    ".$
    -0.06
    astro
    -0.06
    ãģ¾ãģ¾
    -0.06
    estro
    -0.06
    çĻ¾åº¦çŁ¥éģĵ
    -0.06
     Again
    -0.06
    .hex
    -0.06
    POSITIVE LOGITS
    hammer
    0.08
    Ú©ÙĪ
    0.08
    nown
    0.07
    æĸ
    0.07
    Stick
    0.07
    cached
    0.07
    PAL
    0.07
    изи
    0.07
    infeld
    0.07
    ocache
    0.07
    Activations Density 0.254%

    No Known Activations