© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14030
    Prev
    Next
    INDEX
    Explanations

    ( symbols and letters, followed by punctuation

    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
    ä¸ĢåĪĨ
    -0.07
     V
    -0.06
    çŃ
    -0.06
    acket
    -0.06
    tä
    -0.06
     Richter
    -0.06
    rons
    -0.06
    -block
    -0.05
    gid
    -0.05
     séqu
    -0.05
    POSITIVE LOGITS
    AIT
    0.10
    ñera
    0.09
    å±ħçĦ¶æĺ¯
    0.08
    queur
    0.08
    è·¯éĢı
    0.07
    ANNOT
    0.07
    åİŁåŀĭ
    0.07
     berupa
    0.07
    Verk
    0.07
    ogan
    0.07
    Activations Density 0.004%

    No Known Activations