© 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. 48724
    Prev
    Next
    INDEX
    Explanations

    relationships and social connections

    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
    çī¹
    -0.06
    ä¸İåħ¶ä»ĸ
    -0.06
    åºķ
    -0.06
    åıijåĪ°
    -0.06
    iht
    -0.06
    atro
    -0.06
    rots
    -0.06
    ä¸Ńå¿ĥç»Ħ
    -0.06
    neh
    -0.06
    Char
    -0.06
    POSITIVE LOGITS
     secondary
    0.10
    éĹ´æİ¥
    0.10
     indirectly
    0.10
     indire
    0.09
    è¿ŀ带
    0.09
    Secondary
    0.09
    çĭ¬ç«ĭçļĦ
    0.09
    çĭ¬ç«ĭ
    0.09
    åįķçĭ¬çļĦ
    0.09
    secondary
    0.09
    Activations Density 0.353%

    No Known Activations