© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    http://www.apache.org/licenses/LICENSE-2.0

    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
    zar
    -0.08
    éļĪ
    -0.08
    ippet
    -0.07
    ardin
    -0.07
    稽
    -0.07
    WebKit
    -0.07
    åŃļ
    -0.07
    ç»İ
    -0.07
    ä¸ĢèĪ¬ä¸º
    -0.07
    _configure
    -0.07
    POSITIVE LOGITS
    åĵĪå°Ķ
    0.07
    uga
    0.07
    AAA
    0.07
    afa
    0.06
    agne
    0.06
    .nt
    0.06
    éĶĻ
    0.06
    onos
    0.06
    åĬ¨æijĩ
    0.06
    زÙħ
    0.06
    Activations Density 0.234%

    No Known Activations