© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    conditions for older adults

    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
    ÑıÑĤ
    -0.08
    unga
    -0.08
    Õ¹
    -0.07
    轻轻æĿ¾
    -0.06
    mark
    -0.06
    affen
    -0.06
    åĥıæĺ¯
    -0.06
    建ç«ĭåģ¥åħ¨
    -0.06
    iten
    -0.06
    sep
    -0.06
    POSITIVE LOGITS
     outweigh
    0.16
    æĬµæ¶Ī
    0.11
    弥补
    0.11
    æĿĥè¡¡
    0.10
    è¶³å¤Ł
    0.10
    åĪ©
    0.09
     compens
    0.09
     despite
    0.09
     notwithstanding
    0.08
    èĻ½çĦ¶
    0.08
    Activations Density 0.028%

    No Known Activations