© 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. 18737
    Prev
    Next
    INDEX
    Explanations

    social media

    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
    微信åı·
    -0.07
    repid
    -0.07
    éĥ¨èIJ½å®¢
    -0.07
     complexity
    -0.07
     Tore
    -0.06
    æ¶īéĩijèŀį
    -0.06
    æķ¬ä¸ļç²¾ç¥ŀ
    -0.06
     Bitcoins
    -0.06
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.06
    缺
    -0.06
    POSITIVE LOGITS
    çŃīå¹³åı°
    0.12
    /social
    0.11
     social
    0.10
    platform
    0.10
     platforms
    0.10
    该平åı°
    0.10
    å¹³åı°çļĦ
    0.09
     platform
    0.09
     Social
    0.09
    社交
    0.09
    Activations Density 0.144%

    No Known Activations