© 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. 20352
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
    å±
    -0.07
    aker
    -0.07
    ahl
    -0.07
    èĥĨ
    -0.06
    enk
    -0.06
    бо
    -0.06
    rote
    -0.06
    /cs
    -0.06
    è¨Ģä¼ł
    -0.06
    amber
    -0.06
    POSITIVE LOGITS
    éĩľ
    0.07
    relev
    0.07
    大ä¼ļåłĤ
    0.07
    bens
    0.07
    माण
    0.07
    __$
    0.07
     gider
    0.07
    èĦ¸éĥ¨
    0.06
    rogram
    0.06
    .Tx
    0.06
    Activations Density 0.007%

    No Known Activations