© 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. 21538
    Prev
    Next
    INDEX
    Explanations

    printers and contamination

    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
    oss
    -0.07
    ä»Ģä¹Īåij¢
    -0.06
    iani
    -0.06
    å°Ĩå®ĥ
    -0.06
    çļĦæłĩåĩĨ
    -0.06
    rano
    -0.06
    ENDED
    -0.06
    ÑĽÐµ
    -0.06
    .github
    -0.06
    ================================================================
    -0.06
    POSITIVE LOGITS
    enges
    0.08
    ied
    0.07
    svp
    0.07
    stag
    0.07
    ews
    0.07
    almas
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.06
    zim
    0.06
    以åıĬ缸åħ³
    0.06
     Suites
    0.06
    Activations Density 0.032%

    No Known Activations