© 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. 29906
    Prev
    Next
    INDEX
    Explanations

    wisdom, cannabis, sitting, legislative

    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
    ycl
    -0.07
    æ£ł
    -0.07
    akens
    -0.07
    ered
    -0.06
    aggi
    -0.06
    arik
    -0.06
    azz
    -0.06
    prm
    -0.06
    :normal
    -0.06
    å¥Ĺ
    -0.06
    POSITIVE LOGITS
     Martino
    0.08
     stessa
    0.07
    zgl
    0.07
    urtles
    0.07
    èįļ
    0.07
    çĺŁ
    0.07
    åħįä¸įäºĨ
    0.07
    æĽ´å¤§çļĦè´¡çĮ®
    0.07
    æĭīæĭī
    0.06
    âĢ¦**
    0.06
    Activations Density 0.063%

    No Known Activations