© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    results and schedule

    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
    impa
    -0.09
    éĶ¦æ¶Ľ
    -0.08
    ä¼ĺè´¨çļĦ产åĵģ
    -0.07
    pital
    -0.07
    égr
    -0.07
    ä¸ŃåĮº
    -0.07
    ба
    -0.07
     dimas
    -0.07
    纶
    -0.07
    åIJijåīįèµ°
    -0.07
    POSITIVE LOGITS
     Score
    0.07
    çŃĶé¢ĺ
    0.07
    bit
    0.07
     predictive
    0.06
    .br
    0.06
    ξε
    0.06
    -score
    0.06
    .fill
    0.06
    åıĤèĢĥçŃĶæ¡Ī
    0.06
     score
    0.06
    Activations Density 0.003%

    No Known Activations