© 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. 3413
    Prev
    Next
    INDEX
    Explanations

    sampling technique or random sample

    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
    oggles
    -0.07
    illard
    -0.07
    æĿĢæīĭ
    -0.07
     rewritten
    -0.06
    alten
    -0.06
    é¡½åĽº
    -0.06
    Õ®
    -0.06
    iola
    -0.06
    æī£
    -0.06
    åı³è½¬
    -0.06
    POSITIVE LOGITS
    æĬ½æł·
    0.18
     sampling
    0.17
    sampling
    0.16
    æł·æľ¬
    0.15
     Sampling
    0.15
    Sampling
    0.15
     sampled
    0.14
    åıĸæł·
    0.14
     samples
    0.14
    sample
    0.13
    Activations Density 0.047%

    No Known Activations