© 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. 9933
    Prev
    Next
    INDEX
    Explanations

    name, title, or label

    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
     Sachs
    -0.06
    ovski
    -0.06
     pent
    -0.06
     r
    -0.06
    ijnen
    -0.06
     Bh
    -0.06
     bolt
    -0.06
     R
    -0.06
    apon
    -0.06
     relative
    -0.06
    POSITIVE LOGITS
    title
    0.12
     title
    0.12
    /title
    0.12
    _title
    0.11
    :title
    0.10
    	title
    0.10
    /name
    0.10
    ENTITY
    0.10
    ,title
    0.10
    Title
    0.10
    Activations Density 0.292%

    No Known Activations