© 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. 44101
    Prev
    Next
    INDEX
    Explanations

    .sourceforge paths

    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
     TikTok
    -0.18
    æĸĩæĹħ
    -0.16
    https
    -0.16
     emoji
    -0.16
     emojis
    -0.15
    æĬĸéŁ³
    -0.15
     ðŁij
    -0.15
     https
    -0.15
    ï¸ı
    -0.15
    ðŁ
    -0.15
    POSITIVE LOGITS
     idéia
    0.15
    éĿŀåħ¸
    0.12
    èĥ¡éĶ¦æ¶Ľ
    0.12
     AIDS
    0.11
     iPod
    0.11
    æĥŁä¸Ģ
    0.11
    好象
    0.11
     AOL
    0.11
     videot
    0.10
    å¸ĥä»Ģ
    0.10
    Activations Density 12.163%

    No Known Activations