© 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. 42182
    Prev
    Next
    INDEX
    Explanations

    version="1.0"

    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
    igh
    -0.09
    á»IJI
    -0.08
    ãĥ¼ãĥģ
    -0.08
    antal
    -0.07
    ëĪĦ
    -0.07
    è§ģ人
    -0.07
    _DSP
    -0.07
     obsta
    -0.07
     impac
    -0.07
    à¦Ľ
    -0.07
    POSITIVE LOGITS
    undle
    0.06
     rx
    0.06
     "-//
    0.06
    err
    0.06
    0.06
    è¿Ľç¾¤
    0.06
    ï¼Į
    0.06
    ucar
    0.06
     NotImplemented
    0.06
     loco
    0.06
    Activations Density 1.268%

    No Known Activations