© 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. 25890
    Prev
    Next
    INDEX
    Explanations

    amino acid derivatives

    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
    æ²¹æ°Ķ
    -0.08
    çĩĥæ²¹
    -0.08
    ç¦
    -0.07
    aires
    -0.07
     radial
    -0.07
    åĿ
    -0.07
    åĹħ
    -0.07
    çĩĥçħ¤
    -0.07
    æļ§
    -0.07
    .air
    -0.07
    POSITIVE LOGITS
    æ°¨åŁºéħ¸
    0.09
    ç¼
    0.08
    å¤§ä¾ł
    0.08
    protein
    0.08
    mino
    0.08
    éħ¸
    0.08
     β
    0.08
     amino
    0.08
    β
    0.08
    Å¡tu
    0.07
    Activations Density 0.074%

    No Known Activations