© 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. 57790
    Prev
    Next
    INDEX
    Explanations

    plastic bags the votefifth aortic arch: the "great pretender"opened her armsrefuse to toleratetheir new singlestarted yelling at meturn the tableswork harder byworks as hard assit there patiently

    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
    ä¸įåı¯æĢĿè®®
    -0.09
    vision
    -0.08
    æķ´ä¸ªäºº
    -0.08
     myself
    -0.08
    rew
    -0.08
    çļĦ人çĶŁ
    -0.08
    visions
    -0.07
     oneself
    -0.07
    Vision
    -0.07
    èİ·è¯Ħ
    -0.07
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩมัà¸Ļ
    0.10
    å®ĥçļĦ
    0.09
    主人
    0.09
    å®ĥæīĢ
    0.08
    åĩºåħ¶
    0.07
    ç»Ļå®ĥ
    0.07
     itself
    0.07
    让å®ĥ
    0.07
    å®ĥ们
    0.07
    å®ĥéĤ£
    0.07
    Activations Density 0.487%

    No Known Activations