© 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. 17125
    Prev
    Next
    INDEX
    Explanations

    the invention relates to

    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
    éķ°
    -0.07
    ä¸Ģæĭį
    -0.07
    appelle
    -0.07
    羸
    -0.07
    moni
    -0.07
    è´£ç¼ĸ
    -0.07
    esu
    -0.07
     ÐIJдминиÑģÑĤÑĢаÑĨиÑı
    -0.07
    æĹłæĦıéĹ´
    -0.07
    ETY
    -0.07
    POSITIVE LOGITS
    ç¥ŀçİĭ
    0.07
    ÑģелÑĮ
    0.07
    èıģ
    0.07
     ning
    0.07
    ostal
    0.07
    ×ķר×ķת
    0.07
    èĩ£
    0.06
    æĬĽ
    0.06
    åıijå±ķä¸ŃåĽ½å®¶
    0.06
    ervlet
    0.06
    Activations Density 0.390%

    No Known Activations