© 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. 27258
    Prev
    Next
    INDEX
    Explanations

    after "was"

    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
    éĸ±
    -0.07
    好æľĭåıĭ
    -0.07
    icu
    -0.07
    å±Ĭé«ĺä¸ī
    -0.07
    LLU
    -0.06
    åħ«çĻ¾
    -0.06
    ICA
    -0.06
    omini
    -0.06
    pris
    -0.06
    geh
    -0.06
    POSITIVE LOGITS
    aret
    0.09
    oyer
    0.07
    丰åİļ
    0.07
    uston
    0.07
    allet
    0.07
    iran
    0.06
     Britann
    0.06
    ä¸¤æ±Ł
    0.06
    åŃ¦ä¹łç¬Ķè®°
    0.06
    arkin
    0.06
    Activations Density 0.419%

    No Known Activations