© 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. 57047
    Prev
    Next
    INDEX
    Explanations

    specialized psychosocial modules

    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
    _encoded
    -0.08
    _MAJOR
    -0.07
     ÑĦана
    -0.07
    çģĺ
    -0.07
    约车
    -0.07
    edah
    -0.07
    posted
    -0.07
    dos
    -0.07
    åħ¬ä¿¡
    -0.07
     vig
    -0.07
    POSITIVE LOGITS
    åİ®
    0.06
     dedi
    0.06
    æĽ´å¤ļçļĦ人
    0.06
    ä½ľä¸ºä¸Ģç§į
    0.06
    æľīæĿ¡ä»¶çļĦ
    0.06
    pflicht
    0.06
    è®°èĢħä»İ
    0.06
    èĥľ
    0.06
     conditioned
    0.06
    å®Ľ
    0.06
    Activations Density 0.092%

    No Known Activations