© 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. 20105
    Prev
    Next
    INDEX
    Explanations

    port number

    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
    rtl
    -0.08
     Stras
    -0.07
     mild
    -0.07
    æŀķ
    -0.07
    osg
    -0.06
     EFE
    -0.06
    esub
    -0.06
     forg
    -0.06
    ysin
    -0.06
     CDs
    -0.06
    POSITIVE LOGITS
     localhost
    0.09
     Protocol
    0.08
    port
    0.08
     port
    0.08
    emperature
    0.08
    htar
    0.07
    localhost
    0.07
     пÑĢоÑĤо
    0.07
     ports
    0.07
    unic
    0.07
    Activations Density 0.068%

    No Known Activations