© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17964
    Prev
    Next
    INDEX
    Explanations

    ambiguity, effects, corruption, variations

    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
     ficken
    -0.08
    reis
    -0.08
    ä¸įè¯Ĩ
    -0.07
    åĢ¼æѤ
    -0.07
     Wib
    -0.07
    åijĨäºĨ
    -0.07
    è¦ģä¹Īæĺ¯
    -0.07
    aday
    -0.07
     -**
    -0.07
    imai
    -0.07
    POSITIVE LOGITS
    æĺ¾å¾ĹæľīäºĽ
    0.07
    åľ¨æŁIJäºĽ
    0.06
    æŁIJäºĽ
    0.06
     mag
    0.06
     arises
    0.06
     Hex
    0.06
    åĽłä¸ºä»ĸ
    0.06
    vir
    0.06
    ish
    0.06
    .scala
    0.06
    Activations Density 0.206%

    No Known Activations