© 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. 40947
    Prev
    Next
    INDEX
    Explanations

    terminal sequencing, CNBC, park, City, interface, recorder, email, optim

    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
    elp
    -0.07
    好æĥ³
    -0.07
    erber
    -0.07
    æľŃ
    -0.07
    æĪª
    -0.06
    缮ä¸į
    -0.06
    usu
    -0.06
    ä¸į让
    -0.06
     McCart
    -0.06
     câte
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    gre
    0.08
    æ¦Ħ
    0.07
    夷
    0.07
    ä¿ĿéļľæĢ§
    0.07
    tip
    0.07
    éĢĢè´¹
    0.07
    Tip
    0.06
    gó
    0.06
    çī¹
    0.06
    Activations Density 0.741%

    No Known Activations