© 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. 48475
    Prev
    Next
    INDEX
    Explanations

    concentration measurements

    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
    çĤ¹å¯¹
    -0.08
    转贴
    -0.07
    ambah
    -0.07
    onus
    -0.06
    è¾Ħ
    -0.06
    éĩįè¤ĩ
    -0.06
     cấp
    -0.06
     HUT
    -0.06
    بطة
    -0.06
    è¶ħ人
    -0.06
    POSITIVE LOGITS
     concentrations
    0.11
    æµĵ度çļĦ
    0.09
    æµĵ度
    0.08
    Assignable
    0.08
    OSC
    0.08
    åIJĦèĩª
    0.08
    _VARS
    0.08
    çĤ¹åĩ»ä¸ĭæĸ¹
    0.07
     concentration
    0.07
    å£ģæĮĤ
    0.07
    Activations Density 0.002%

    No Known Activations