© 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. 44061
    Prev
    Next
    INDEX
    Explanations

    without

    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
    浩çĦ¶
    -0.08
     uite
    -0.08
    anei
    -0.07
    anos
    -0.07
    janya
    -0.07
     atof
    -0.07
    itime
    -0.07
    ä»»ä½ķ责任
    -0.07
    ãģ¾ãģĹãģŁ
    -0.07
    éĢļè¿ĩå°Ĩ
    -0.07
    POSITIVE LOGITS
    emel
    0.09
     proper
    0.08
     Proper
    0.07
    ä¸Ģå®ļçļĦ
    0.07
    å°Ķæĸ¯
    0.07
    thur
    0.07
     properly
    0.07
    proper
    0.07
    åģ¥åħ¨çļĦ
    0.07
     explicit
    0.07
    Activations Density 0.088%

    No Known Activations