© 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. 21240
    Prev
    Next
    INDEX
    Explanations

    seize property

    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
    Ļ
    -0.07
    åĽ½å¼º
    -0.07
    ijIJ
    -0.06
    åĨħæķĽ
    -0.06
     reversible
    -0.06
    aux
    -0.06
    ä¹īè¯į
    -0.06
    ourcem
    -0.06
    imbus
    -0.06
    æŃ£æľ¬
    -0.06
    POSITIVE LOGITS
    isia
    0.08
    wez
    0.08
    roz
    0.08
    ниÑĤи
    0.08
    iris
    0.08
    appare
    0.07
    移
    0.07
    andler
    0.07
    िला
    0.07
    zust
    0.07
    Activations Density 0.002%

    No Known Activations