© 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. 55768
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators and results

    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
    ención
    -0.07
    tres
    -0.07
    (each
    -0.07
    inta
    -0.07
     Coleman
    -0.07
    ä¼ģä¸ļä¸ļåĬ¡
    -0.07
    izzer
    -0.07
    çİīåħ°
    -0.07
    è¶ħéĻIJ
    -0.07
    .ErrorMessage
    -0.06
    POSITIVE LOGITS
    å°±æīĵ
    0.08
     slightly
    0.07
    æıIJ
    0.07
    aug
    0.07
    åĪ
    0.07
    ç¨įå¾®
    0.07
    -plus
    0.07
    æĶ¹èī¯
    0.07
     nette
    0.07
    çķ¥å¾®
    0.07
    Activations Density 0.124%

    No Known Activations