© 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. 30783
    Prev
    Next
    INDEX
    Explanations

    secretase, magnesium, grass, busy, distract

    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
    gone
    -0.08
    IMER
    -0.08
    ä¸ĩå¹´
    -0.08
    sgi
    -0.08
    zien
    -0.07
    tar
    -0.07
    太éĥİ
    -0.07
    è¿İåIJĪ
    -0.07
    èİ
    -0.07
    วà¸Ļ
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥æľīæķĪ
    0.12
    åĮĸ解
    0.11
    æĬµå¾¡
    0.11
    åı¯ä»¥èµ·åĪ°
    0.10
    åı¯ä»¥åĩıå°ij
    0.10
    åı¯ä»¥æľīæķĪåľ°
    0.10
     mitig
    0.10
    èĥ½å¤ŁæľīæķĪ
    0.10
     protective
    0.10
    æĬµæ¶Ī
    0.10
    Activations Density 0.314%

    No Known Activations