© 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. 27105
    Prev
    Next
    INDEX
    Explanations

    outer"..."dimensional"

    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
    velle
    -0.08
    çĮľä½łåĸľæ¬¢
    -0.08
     polém
    -0.07
    _SOL
    -0.07
    åħģ
    -0.07
     insanely
    -0.07
    eno
    -0.07
    à¸ĩ
    -0.07
    èĢĮæĺĵ
    -0.07
    éal
    -0.07
    POSITIVE LOGITS
    Outer
    0.07
     Outer
    0.06
     presumably
    0.06
    é¸
    0.06
    å¿Ļ
    0.06
     outer
    0.05
    æµĴ
    0.05
    æijĩæijĩ头
    0.05
    åįĥæĸ¹
    0.05
    æ¦ľ
    0.05
    Activations Density 0.049%

    No Known Activations