© 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. 19998
    Prev
    Next
    INDEX
    Explanations

    chemistry and cognition

    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
    ÑģÑı
    -0.09
    য়à§ĩ
    -0.08
    vá
    -0.08
    ÙİÙijب
    -0.07
    بت
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    à¸Ļà¹īำ
    -0.07
    å°±å½ĵ
    -0.07
    Ñĥж
    -0.07
    anes
    -0.07
    POSITIVE LOGITS
    ically
    0.09
    ingle
    0.08
    inet
    0.08
    irn
    0.07
    oug
    0.07
    alt
    0.07
     ê´Ģ볨ëIJľ
    0.07
     ÙĪاÙĦعاÙĦÙħ
    0.07
    iest
    0.07
    alg
    0.07
    Activations Density 1.282%

    No Known Activations