© 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. 49638
    Prev
    Next
    INDEX
    Explanations

    amino group

    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
    /filter
    -0.07
    æĭĶ
    -0.07
    cd
    -0.07
    æĭ¨
    -0.06
    æµij身
    -0.06
    zar
    -0.06
     unfold
    -0.06
    åīįèĮħ
    -0.06
    èĢĥ
    -0.06
    åĩĭ
    -0.06
    POSITIVE LOGITS
    åĺ¿
    0.08
    æ´»
    0.08
    undler
    0.08
    åı¦ä¸Ģæĸ¹
    0.07
    _INLINE
    0.07
    opic
    0.07
    bian
    0.07
    à¸ģรี
    0.07
     Decorating
    0.07
    -minus
    0.07
    Activations Density 0.015%

    No Known Activations