© 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. 3827
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    ä½ľåĪĻ
    -0.09
     بث
    -0.08
    æľīåħ³æĥħåĨµ
    -0.08
    iera
    -0.07
    ë§ī
    -0.07
    æ¯Ķè¾ĥå¤ļ
    -0.07
    indra
    -0.07
    èIJ¥æķij
    -0.07
    æĪĸåħ¶
    -0.07
    strt
    -0.07
    POSITIVE LOGITS
     +
    0.10
    )+(
    0.09
     plus
    0.08
     плÑİÑģ
    0.08
    "+"
    0.08
    +l
    0.08
    åĬłä¸Ĭ
    0.08
    +w
    0.07
    +p
    0.07
    +n
    0.07
    Activations Density 0.001%

    No Known Activations