© 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. 20453
    Prev
    Next
    INDEX
    Explanations

    quantifiers like all, each, many, any

    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
    otor
    -0.08
    ossi
    -0.08
    åįĬå±±
    -0.08
    WebpackPlugin
    -0.07
    ellas
    -0.07
    besondere
    -0.07
    ynet
    -0.07
    psc
    -0.07
    æºĸ
    -0.07
    ever
    -0.07
    POSITIVE LOGITS
    Äįov
    0.06
    åŃ£
    0.06
    æ¡ĤåĨł
    0.06
    apo
    0.06
    _occ
    0.06
     thro
    0.06
     interp
    0.06
    æĩIJ
    0.06
    åıĤåĬłçļĦ
    0.06
    wij
    0.06
    Activations Density 0.440%

    No Known Activations