© 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. 40279
    Prev
    Next
    INDEX
    Explanations

    DC converter, focal segmental, multiple zeta, allog, identical twins, railway cars, organic light, phase locked, green glass, younger guy

    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
    ETERS
    -0.06
    ke
    -0.06
    िल
    -0.06
    ela
    -0.06
    è¨Ģ
    -0.06
    åıĬ以ä¸Ĭ
    -0.06
    æīī
    -0.06
    ìłģìĿ¸
    -0.06
    FFFFFFFF
    -0.06
    æĥ³çļĦ
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.09
    jong
    0.08
    fone
    0.08
    丽åįİ
    0.08
    çīĪä¸ĭè½½
    0.08
    anja
    0.07
    jami
    0.07
    wis
    0.07
    ç»Īå°Ĩ
    0.07
    ì°©
    0.07
    Activations Density 0.869%

    No Known Activations