© 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. 37878
    Prev
    Next
    INDEX
    Explanations

    gestation or sexual organs

    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
    太éĥİ
    -0.06
    ebro
    -0.06
    å¾·å°Ķ
    -0.06
    ...
    -0.06
    æĺ¯ä¸Ģ个éĿŀ常
    -0.06
    åĪ°ä¸Ģ个
    -0.05
     somehow
    -0.05
    çī¹åĪ«
    -0.05
    ION
    -0.05
    RO
    -0.05
    POSITIVE LOGITS
    astia
    0.08
    å¿ĥå¾ĭ
    0.08
    éri
    0.08
    hejiang
    0.08
    MODULE
    0.08
    ittel
    0.07
    éĶģ骨
    0.07
    对ä¸Ĭè¿°
    0.07
    enames
    0.07
    鼷æĸ¯
    0.07
    Activations Density 0.037%

    No Known Activations