© 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. 10308
    Prev
    Next
    INDEX
    Explanations

    network port checks

    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
    éģIJ
    -0.07
     https
    -0.07
    https
    -0.07
    arau
    -0.07
    వా
    -0.07
    è¡·
    -0.07
    /interfaces
    -0.07
    empf
    -0.07
    æĬĺ
    -0.06
    /tty
    -0.06
    POSITIVE LOGITS
    _constraints
    0.09
    _constraint
    0.08
     constraint
    0.08
     constraints
    0.08
    constraints
    0.08
    пан
    0.08
    reation
    0.08
     Constraint
    0.07
    constraint
    0.07
    ancel
    0.07
    Activations Density 0.006%

    No Known Activations