© 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. 22556
    Prev
    Next
    INDEX
    Explanations

    numbers and code syntax

    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
     bilanci
    -0.08
    Äįin
    -0.07
    bach
    -0.07
    -bal
    -0.07
    GRAM
    -0.07
    atham
    -0.07
    .DOM
    -0.07
    ppi
    -0.06
     balanced
    -0.06
    asso
    -0.06
    POSITIVE LOGITS
    å¾Ĵ
    0.08
    å½Ĵäºİ
    0.08
    åıªè¦ģæľī
    0.08
    å½Ĵç±»
    0.08
    çľĭä¸įæ¸ħ
    0.08
    绣ä¸ĢåĪ°
    0.07
     oversized
    0.07
    ä½łåıªè¦ģ
    0.07
    ä¸įç®¡ä½ł
    0.07
     lump
    0.07
    Activations Density 0.104%

    No Known Activations