© 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. 39752
    Prev
    Next
    INDEX
    Explanations

    auto height and flex grow

    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
    缸åħ³æݨèįIJ
    -0.07
    IDs
    -0.07
    counts
    -0.07
    çĶŁæ´»ä¼ļ
    -0.06
     swirling
    -0.06
     reversal
    -0.06
    åħ¹
    -0.06
     ná»ĵng
    -0.06
     blot
    -0.06
     swirl
    -0.06
    POSITIVE LOGITS
    ToFit
    0.09
    elastic
    0.08
    å¼¹æĢ§
    0.08
    æĪIJéķ¿
    0.08
     maxWidth
    0.08
    flex
    0.08
     allotted
    0.08
     flex
    0.08
    Width
    0.08
    asonry
    0.08
    Activations Density 0.123%

    No Known Activations