© 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. 40435
    Prev
    Next
    INDEX
    Explanations

    can followed by a verb

    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
    gül
    -0.08
    gnore
    -0.08
    æīİå®ŀåģļ好
    -0.08
    ãģĬãĤĤ
    -0.08
    cbd
    -0.08
    indsight
    -0.08
    acman
    -0.08
     spiagg
    -0.08
    åı¯ä»¥ä¸º
    -0.07
     poter
    -0.07
    POSITIVE LOGITS
    't
    0.14
    ’t
    0.14
     be
    0.12
    -être
    0.11
     saja
    0.10
    nt
    0.09
    /w
    0.09
    ning
    0.09
    ister
    0.09
    ´t
    0.09
    Activations Density 0.270%

    No Known Activations