© 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. 3779
    Prev
    Next
    INDEX
    Explanations

    afferent pathways

    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
    iseurs
    -0.07
    ä¸ī项
    -0.07
    åĽĽé¡¹
    -0.07
    udev
    -0.07
    xCD
    -0.07
    Ã¶ÃŁe
    -0.07
    代ä¹ĭ
    -0.07
    æĶ¾ä¸Ĭ
    -0.06
    å½ĵä¹ĭ
    -0.06
     ration
    -0.06
    POSITIVE LOGITS
     pathways
    0.10
     relay
    0.10
    åĪĿ级
    0.09
     pathway
    0.09
    ä¸Ńæŀ¢
    0.09
    relay
    0.09
    éĢļè·¯
    0.09
     neural
    0.09
    éĢĶå¾Ħ
    0.08
     Relay
    0.08
    Activations Density 0.111%

    No Known Activations