© 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. 11230
    Prev
    Next
    INDEX
    Explanations

    Clock, calculator, daytime daemon, modulus

    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
    omot
    -0.08
    çݰ身
    -0.08
    ä¸Ńåħ´
    -0.07
     arrec
    -0.07
    éĶ¦æłĩ
    -0.07
     hadir
    -0.07
    轻信
    -0.07
    indel
    -0.07
     :+:
    -0.07
    upe
    -0.07
    POSITIVE LOGITS
    _UD
    0.07
     Uh
    0.07
    以确å®ļ
    0.07
    egram
    0.06
    ¹
    0.06
    _batches
    0.06
    è¾°
    0.06
     fractional
    0.06
    第ä¸Ģåį°è±¡
    0.06
     Thumbnails
    0.06
    Activations Density 0.001%

    No Known Activations