© 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. 32878
    Prev
    Next
    INDEX
    Explanations

    oriented Riemannian manifold

    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
    keit
    -0.08
    软åĮĸ
    -0.07
    heil
    -0.07
    çĦ¦ç³ĸ
    -0.07
    麹
    -0.07
    soft
    -0.07
     overhe
    -0.07
    å§ijèĭı
    -0.07
    åħ¥åij³
    -0.07
    éĢ
    -0.07
    POSITIVE LOGITS
    volume
    0.10
    -volume
    0.09
     volume
    0.09
    åıī
    0.09
    ä½ĵ积
    0.08
    _signed
    0.08
     determinant
    0.08
     biv
    0.08
     Volume
    0.08
     volumes
    0.07
    Activations Density 0.004%

    No Known Activations