© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    strontium titanate

    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
    çļĦè¿ĺæľī
    -0.09
    urst
    -0.08
    æĶ¾å¼Ģ
    -0.07
    çļĦéĥ½æĺ¯
    -0.07
    pth
    -0.07
    auta
    -0.07
    esten
    -0.07
     Onion
    -0.07
    åĵŁ
    -0.07
    大æĪĺ
    -0.07
    POSITIVE LOGITS
    ีà¸ģ
    0.07
    antar
    0.07
    اء
    0.07
    ÙĪÙĨÙĬØ©
    0.06
    ignet
    0.06
     igen
    0.06
    é£Ĵ
    0.06
    engew
    0.06
     abbreviated
    0.06
    знакомиÑĤÑĮÑģÑı
    0.06
    Activations Density 0.017%

    No Known Activations