© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    superlatives or lists

    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
    ì¶ķ
    -0.08
    yled
    -0.08
    insky
    -0.08
    彿
    -0.08
    ]>
    -0.07
    prech
    -0.07
    çij¾
    -0.07
    aland
    -0.07
    ả
    -0.07
    swick
    -0.07
    POSITIVE LOGITS
    åĺĺ
    0.07
    æŁIJç§į
    0.07
     oldest
    0.06
    óp
    0.06
     ekstrem
    0.06
    elus
    0.06
     extreme
    0.06
    infeld
    0.06
    åĪ°æŀģèĩ´
    0.06
     dise
    0.06
    Activations Density 0.002%

    No Known Activations