© 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. 62932
    Prev
    Next
    INDEX
    Explanations

    via, by, through, 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
    گاÙĨ
    -0.09
    naud
    -0.07
    åī²ãĤĬ
    -0.07
    uxtap
    -0.07
    zag
    -0.07
    angkat
    -0.07
     Rücks
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    baran
    -0.07
     à¤Ĺर
    -0.07
    POSITIVE LOGITS
    主è¦ģéĢļè¿ĩ
    0.15
    éĹ´æİ¥
    0.14
    主è¦ģæĺ¯éĢļè¿ĩ
    0.14
     indirect
    0.13
     via
    0.13
    缴æİ¥æĪĸéĹ´æİ¥
    0.12
     indirectly
    0.12
    éĢĶå¾Ħ
    0.12
     indire
    0.12
    via
    0.12
    Activations Density 0.194%

    No Known Activations