© 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. 8744
    Prev
    Next
    INDEX
    Explanations

    land owner

    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
    é«ĺçħ§
    -0.09
    æĹłéĹ»
    -0.08
    æµ·èŀº
    -0.08
    avanaugh
    -0.08
    ï¸İ
    -0.07
    kens
    -0.07
    ä¸įè¡°
    -0.07
    IMUM
    -0.07
    TextLabel
    -0.07
    ủa
    -0.07
    POSITIVE LOGITS
    owner
    0.10
     Äijai
    0.09
     vá»±c
    0.09
    owners
    0.09
    ierungs
    0.08
    èĤ¥æ²ĥ
    0.08
    wirtschaft
    0.08
    wagon
    0.08
    bag
    0.07
    ä¸ĬçļĦ
    0.07
    Activations Density 0.035%

    No Known Activations