© 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. 27541
    Prev
    Next
    INDEX
    Explanations

    is followed by classification

    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
     ìĿ´ëĬĶ
    -0.10
     spiagg
    -0.10
    ä¸Ģè¾ĪåŃIJ
    -0.09
     ìļ°ë¦¬ëĬĶ
    -0.09
    ãģĦãĤī
    -0.09
    ãģĦ
    -0.09
    ãģĦãģį
    -0.09
    ãģĦãģ¾
    -0.09
    ãģĦãģıãģ¤ãģĭ
    -0.09
    ãģĵãģ¡ãĤī
    -0.09
    POSITIVE LOGITS
    /is
    0.17
    otope
    0.16
    nt
    0.13
    /w
    0.12
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
    olation
    0.11
    olate
    0.10
     indeed
    0.10
    à¹Ħà¸Ľà¸ķาม
    0.10
    omer
    0.10
    Activations Density 2.384%

    No Known Activations