© 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. 64616
    Prev
    Next
    INDEX
    Explanations

    manifold decomposition

    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
    ehme
    -0.11
    ãģ¾ãģĹãģ¦
    -0.09
    annis
    -0.09
    undas
    -0.08
    avanaugh
    -0.08
    á»±ng
    -0.08
    umar
    -0.08
    infeld
    -0.08
    engel
    -0.08
    à¸Ĭะ
    -0.08
    POSITIVE LOGITS
    hattan
    0.12
    UFACT
    0.10
    ifest
    0.09
    ufaktur
    0.09
    IFEST
    0.09
    schede
    0.08
    ufacturer
    0.08
    ifold
    0.08
    atee
    0.08
            ↵        ↵        ↵
    0.08
    Activations Density 0.082%

    No Known Activations