© 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. 39472
    Prev
    Next
    INDEX
    Explanations

    unofficial, implicit, informal

    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
     Pen
    -0.07
    åĪĨè£Ĥ
    -0.07
    ç¬Ķ
    -0.06
    å¯Ħ宿
    -0.06
     enslaved
    -0.06
    äºĮæľ¬
    -0.06
    Pen
    -0.06
    rig
    -0.06
    çĭĤæļ´
    -0.06
    åħ¨æł¡
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶æ²¡æľī
    0.15
     informal
    0.12
    èĻ½çĦ¶ä¸įæĺ¯
    0.10
     unofficial
    0.10
    implicit
    0.10
     makeshift
    0.10
     implicitly
    0.10
    implicitly
    0.10
    大èĩ´
    0.10
    Implicit
    0.10
    Activations Density 0.962%

    No Known Activations