© 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. 27033
    Prev
    Next
    INDEX
    Explanations

    performance improvements

    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
    Disposition
    -0.07
    .dtd
    -0.07
    Reviews
    -0.07
    åħ¶éĹ´
    -0.07
    ãĥijãĥ¼ãĥĪ
    -0.07
    umah
    -0.07
     intimately
    -0.07
    ventario
    -0.07
    常è§ģçļĦ
    -0.07
    prib
    -0.07
    POSITIVE LOGITS
     results
    0.10
    results
    0.09
    .results
    0.08
    _results
    0.08
     Results
    0.08
     iterations
    0.08
     improvements
    0.08
     noticeably
    0.08
    iterations
    0.08
     optim
    0.08
    Activations Density 0.058%

    No Known Activations