© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    transform, convert, rewrite

    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
    pek
    -0.07
    被åħ³éĹŃ
    -0.07
    æĩĴæķ£
    -0.07
    å¤ļåŃĶ
    -0.06
    saved
    -0.06
    ogh
    -0.06
    dirs
    -0.06
    arp
    -0.06
    åıĪå¼Ģå§ĭ
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
     beforehand
    0.11
     préalable
    0.10
     before
    0.09
    绣ä¸ĢåĪ°
    0.09
    转åĮĸ
    0.09
     Before
    0.09
     dahulu
    0.09
    åľ¨è¿Ľåħ¥
    0.08
     artificially
    0.08
    Before
    0.08
    Activations Density 0.139%

    No Known Activations