© 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. 56690
    Prev
    Next
    INDEX
    Explanations

    telecommunications network

    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
    obb
    -0.07
    fx
    -0.07
    ä¸Ģ缴éĥ½
    -0.07
    KK
    -0.06
    ä¸ĢåIJij
    -0.06
    oor
    -0.06
    è³Ģ
    -0.06
    à¸Ħะ
    -0.06
    å¹´çļĦæŶåĢĻ
    -0.06
    iris
    -0.06
    POSITIVE LOGITS
     Mitar
    0.08
    yntax
    0.08
    aira
    0.07
    олÑĮ
    0.07
    ERV
    0.07
    нав
    0.07
    ades
    0.07
    ervation
    0.07
    æĪ´å°Ķ
    0.07
    åłµ
    0.07
    Activations Density 0.007%

    No Known Activations