© 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. 18888
    Prev
    Next
    INDEX
    Explanations

    direction, kind, rear, rates, rims, Hwy

    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
    年纪
    -0.08
    ẩm
    -0.08
    伯çĪµ
    -0.07
    éĢĤé¾Ħ
    -0.07
    èĩªå·±çļĦçĶŁåij½
    -0.06
    没æľīæī¾åĪ°
    -0.06
    渺å°ı
    -0.06
    fatal
    -0.06
    tributes
    -0.06
    jder
    -0.06
    POSITIVE LOGITS
    åĮºåĪ«
    0.09
     separate
    0.08
    æľīåĪ«
    0.08
     ëĶ°ë¡ľ
    0.08
     asym
    0.08
    çĶ¨äºİ
    0.08
     rates
    0.08
    ä¸įä¸Ģèĩ´
    0.08
     distinct
    0.08
     disparity
    0.08
    Activations Density 0.092%

    No Known Activations