© 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. 63076
    Prev
    Next
    INDEX
    Explanations

    places in Jordan Valley, Italy, or Spain

    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
    è¦ģåĽł
    -0.07
    _sampler
    -0.06
     Glover
    -0.06
    amore
    -0.06
    éģIJ
    -0.06
    符åIJĪè¦ģæ±Ĥ
    -0.06
     Season
    -0.06
    ool
    -0.06
    æºIJäºİ
    -0.06
    uo
    -0.06
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    æĪĸåħ¶å®ĥ
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
    stens
    0.07
     milione
    0.07
    ipse
    0.07
    âĤ¬âĦ¢
    0.07
     Allem
    0.07
    stra
    0.07
    atici
    0.07
    Activations Density 0.593%

    No Known Activations