© 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. 19922
    Prev
    Next
    INDEX
    Explanations

    . or !

    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
    ers
    -0.08
    ť
    -0.07
    ack
    -0.07
    dest
    -0.07
    erse
    -0.06
    tras
    -0.06
    ersch
    -0.06
    ief
    -0.06
    eri
    -0.06
    elih
    -0.06
    POSITIVE LOGITS
    éĵģé¾Ļ
    0.08
    tui
    0.07
    á»ĭa
    0.07
    ấu
    0.07
    iola
    0.07
     realise
    0.07
    æĿ¥äºº
    0.07
    èĥ½å¤Łä½¿
    0.07
    çĶĦåĪ«
    0.07
    åĩºäºº
    0.07
    Activations Density 2.844%

    No Known Activations