© 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. 13674
    Prev
    Next
    INDEX
    Explanations

    uptake, acquisition, absorption

    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
     Roland
    -0.08
    estu
    -0.08
     pops
    -0.07
     combust
    -0.07
     fires
    -0.07
    æ°´çģ«
    -0.07
    éĺ²çģ«
    -0.07
    _EDITOR
    -0.07
    æıŃ
    -0.07
    olean
    -0.07
    POSITIVE LOGITS
    æijĦåıĸ
    0.12
     uptake
    0.11
    çļĦåIJ¸æĶ¶
    0.10
     avid
    0.09
    æijĦåħ¥
    0.09
    æijĦ
    0.09
    åIJ¸æĶ¶
    0.08
     assim
    0.08
    éĢıè¿ĩ
    0.08
     nutrient
    0.08
    Activations Density 0.071%

    No Known Activations