© 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. 27671
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and timestamps

    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
    iry
    -0.09
    idan
    -0.07
    马é¾Ļ
    -0.07
    éĶ¦æłĩ
    -0.07
    rides
    -0.07
     pas
    -0.07
    abor
    -0.07
    áĢ±áĢ¬áĢĦáĢºáĢ¸
    -0.06
    ضÙħ
    -0.06
    åı·
    -0.06
    POSITIVE LOGITS
    iece
    0.08
    andie
    0.07
    ặng
    0.07
    ç¿ĺ
    0.07
    пали
    0.07
    å±ģèĤ¡
    0.07
     [âĢ¦]
    0.06
     Er
    0.06
    æss
    0.06
    iese
    0.06
    Activations Density 0.008%

    No Known Activations