© 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. 65084
    Prev
    Next
    INDEX
    Explanations

    Protein extract and fluid

    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
    attan
    -0.09
    emez
    -0.08
    èĥ½åģļåĪ°
    -0.08
    linge
    -0.08
     dominated
    -0.07
    جاÙĩ
    -0.07
    elingen
    -0.07
    éľĢè¦ģç»ıè¿ĩ
    -0.07
     OVERRIDE
    -0.07
     Requires
    -0.07
    POSITIVE LOGITS
    çļĦä½ľçĶ¨æĺ¯
    0.14
    æľīåĬ©äºİ
    0.12
    èµ·åĪ°
    0.12
    åı¯ä»¥èµ·åĪ°
    0.12
    åĬ©äºİ
    0.11
     helps
    0.11
    çĶ¨ä»¥
    0.11
    çļĦä½ľçĶ¨
    0.11
    à¸Ĭà¹Īวยลà¸Ķ
    0.10
    èµ·åĪ°äºĨ
    0.10
    Activations Density 0.154%

    No Known Activations