© 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. 39677
    Prev
    Next
    INDEX
    Explanations

    description and coverage

    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
    åºĶçĶ¨åĪ°
    -0.07
    çļĦè¿IJçĶ¨
    -0.07
    ForKey
    -0.07
    åºĶçĶ¨äºİ
    -0.06
    çļĦ使çĶ¨
    -0.06
    XY
    -0.06
    éķ¿æľŁä½¿çĶ¨
    -0.06
    opus
    -0.06
    äinen
    -0.06
    artin
    -0.06
    POSITIVE LOGITS
    å°½æĶ¶
    0.09
    éĢļè¿ĩæŃ¤æ¬¡
    0.09
    æ·ĭæ¼ĵå°½èĩ´
    0.08
    éĢļè¿ĩæľ¬æ¬¡
    0.08
    covered
    0.08
    uard
    0.08
    aged
    0.08
    Included
    0.08
    sep
    0.07
    elib
    0.07
    Activations Density 0.186%

    No Known Activations