© 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. 57147
    Prev
    Next
    INDEX
    Explanations

    room for

    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
    ammen
    -0.11
    thon
    -0.10
    stral
    -0.10
     Insg
    -0.10
    OLVE
    -0.10
    ROTO
    -0.10
    aum
    -0.10
    qrt
    -0.10
    ÂŃt
    -0.10
    ëłģ
    -0.10
    POSITIVE LOGITS
    s
    0.10
    ת
    0.09
    ×ķ
    0.09
    Ùĩ
    0.09
    u
    0.09
    Ñı
    0.08
    (
    0.08
    -
    0.07
    o
    0.07
    t
    0.07
    Activations Density 0.063%

    No Known Activations