© 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. 63492
    Prev
    Next
    INDEX
    Explanations

    reflecting surfaces

    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
    çĶľèľľçļĦ
    -0.07
    rung
    -0.07
     tense
    -0.07
    解æķij
    -0.07
    ä¸ŃåŃĹ
    -0.07
     cramped
    -0.06
    RING
    -0.06
    ç´§å¼łçļĦ
    -0.06
     tension
    -0.06
     whirl
    -0.06
    POSITIVE LOGITS
    åıįå°Ħ
    0.11
    bedo
    0.10
     réfléch
    0.10
     reflective
    0.10
    æ¶Ĥå±Ĥ
    0.09
     specular
    0.09
    åIJ¸æĶ¶
    0.09
    Reflect
    0.09
    åıįåħī
    0.09
    reflect
    0.09
    Activations Density 0.018%

    No Known Activations