© 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. 22290
    Prev
    Next
    INDEX
    Explanations

    rebound, reflection, bounce

    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
    :mm
    -0.08
    locker
    -0.07
    åħ¶äºĭ
    -0.07
    è¿Ľæ°Ķæł¼æłħ
    -0.07
    èĩªæĭĶ
    -0.07
    æ¡¥åĮº
    -0.07
    ijľ
    -0.07
    amme
    -0.07
    å¼ĢçĿĢ
    -0.07
    Ãİ
    -0.06
    POSITIVE LOGITS
    åıįå¼¹
    0.12
    åıįå°Ħ
    0.12
     rebound
    0.12
     rebounds
    0.11
    åıįå½Ī
    0.11
    åĽŀ
    0.10
     reflection
    0.10
     bounce
    0.10
    reflection
    0.10
     reflect
    0.10
    Activations Density 0.013%

    No Known Activations