© 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. 46065
    Prev
    Next
    INDEX
    Explanations

    reflection and deflection

    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
    æŃ¥åŃIJ
    -0.07
    溶
    -0.07
    æĭĶ
    -0.07
    åİĭ缩åĮħ
    -0.07
     Freeze
    -0.06
    _PULL
    -0.06
    æ¸ĹéĢı
    -0.06
    浸泡
    -0.06
    .pull
    -0.06
     Fus
    -0.06
    POSITIVE LOGITS
    åıįå°Ħ
    0.13
     redirect
    0.12
     redirection
    0.11
    redirect
    0.11
     specular
    0.11
     reflection
    0.10
     deflect
    0.10
    Redirect
    0.10
     redirects
    0.10
    .redirect
    0.10
    Activations Density 0.026%

    No Known Activations