© 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. 9195
    Prev
    Next
    INDEX
    Explanations

    sediment, acronym, /local

    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
    uer
    -0.07
    ãĢIJ
    -0.06
    еÑĤÑĮ
    -0.05
    大åIJī
    -0.05
    .
    -0.05
    reen
    -0.05
    -0.05
    et
    -0.05
     M
    -0.05
    erv
    -0.05
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.11
    åĬłæĭ¿å¤§
    0.11
    俱ä¹IJéĥ¨
    0.10
    æĸ°åĬłåĿ¡
    0.10
    åĭ¤åĭ¤æģ³æģ³
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    uhe
    0.09
    ä¸įåı¯æĢĿè®®
    0.08
     pathMatch
    0.08
    书åIJ§
    0.08
    Activations Density 0.011%

    No Known Activations