© 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. 31263
    Prev
    Next
    INDEX
    Explanations

    joining partners, neighbors, cells

    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
    éħĿéħ¿
    -0.07
    abouts
    -0.06
     занÑıÑĤоÑģÑĤи
    -0.06
    akarta
    -0.06
    _EXPRESSION
    -0.06
    æĹ©çŁ¥éģĵ
    -0.06
    åįĬå±±
    -0.06
    à¹Ģลà¸Ĥ
    -0.06
    åĽŃè·¯
    -0.05
    ells
    -0.05
    POSITIVE LOGITS
    人ä¸İ人ä¹ĭéĹ´
    0.16
    人ä¸İ人
    0.16
    ä¸İä»ĸ人
    0.15
     partner
    0.13
     mutual
    0.13
     neighbor
    0.13
     interoper
    0.13
    ç»ĵ对
    0.12
     peer
    0.12
     between
    0.12
    Activations Density 1.015%

    No Known Activations