© 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. 12118
    Prev
    Next
    INDEX
    Explanations

    Ch, Main, Th, Roman, Fol, Gn, Le prefixes

    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
    èĩªæµģ
    -0.07
    åĪ°å°¾
    -0.07
    acy
    -0.07
    _CPP
    -0.07
    å·´æİĮ
    -0.07
    osta
    -0.06
    alh
    -0.06
    atis
    -0.06
    ç»ĻåĪ«äºº
    -0.06
    ŀ
    -0.06
    POSITIVE LOGITS
    å±ĭãģķãĤĵ
    0.08
    åį´ä¹Ł
    0.08
    çĶ±äºİåħ¶
    0.07
    俱ä¹IJéĥ¨
    0.07
    chers
    0.07
    vere
    0.07
    lesa
    0.07
    æ·±éĢł
    0.07
    âĹĨ
    0.07
    æł¹æį®åħ¶
    0.07
    Activations Density 0.038%

    No Known Activations