© 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. 48480
    Prev
    Next
    INDEX
    Explanations

    post-installation messages

    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
    åįķåŃIJ
    -0.07
    带çĬ¶
    -0.06
    ümü
    -0.06
    ikov
    -0.06
    碰åĪ°äºĨ
    -0.06
    izas
    -0.06
    çĭĢ
    -0.06
    æĺ¯è®©
    -0.06
    çĹ´åijĨ
    -0.06
    æĭīèIJ¨
    -0.06
    POSITIVE LOGITS
    erti
    0.08
    iddle
    0.08
    iews
    0.07
    _lite
    0.07
     Uncategorized
    0.07
    æĸ¹å¼ı使çĶ¨
    0.07
    -gnu
    0.07
    redit
    0.07
    fram
    0.07
    oint
    0.07
    Activations Density 0.039%

    No Known Activations