© 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. 30397
    Prev
    Next
    INDEX
    Explanations

    explaining how things basically work

    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
    ennie
    -0.07
    engk
    -0.07
    à¤Ĺत
    -0.07
    ç»ĵ转
    -0.07
    ift
    -0.07
    ober
    -0.07
    å½ĴåĬŁäºİ
    -0.07
    ingg
    -0.07
    ়
    -0.07
    æİĪæĿĥçļĦ
    -0.07
    POSITIVE LOGITS
     essentially
    0.11
     basically
    0.10
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
     insomma
    0.08
     Essentially
    0.07
    æĪ¿å¸Ĥ
    0.07
    ä»¿ä½Ľåľ¨
    0.07
     probably
    0.07
     presumably
    0.07
    åIJįåī¯åħ¶å®ŀ
    0.07
    Activations Density 0.008%

    No Known Activations