© 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. 12981
    Prev
    Next
    INDEX
    Explanations

    subsequent sequences

    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
    æĹłå¤Ħ
    -0.07
    åĩŃ空
    -0.06
    èĢĮåĩºçİ°
    -0.06
    äºķ
    -0.06
    _lookup
    -0.06
    ombe
    -0.06
    缴æİ¥
    -0.06
    è¿İ
    -0.06
    equ
    -0.06
    æµģ
    -0.06
    POSITIVE LOGITS
     thereafter
    0.13
    åħ¶ä½Ļ
    0.11
    以æŃ¤ä¸º
    0.11
    åIJİç»Ń
    0.11
     subsequent
    0.11
    åIJİç»ŃçļĦ
    0.11
    çļĦåħ¶ä»ĸ
    0.10
    èĩªæѤ
    0.10
    å¾ĮçºĮ
    0.10
    ä»ħæѤ
    0.10
    Activations Density 0.411%

    No Known Activations