© 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. 20367
    Prev
    Next
    INDEX
    Explanations

    spatial derivatives and equations

    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
    anser
    -0.07
    uada
    -0.07
    ãĥ©ãĥ³ãĥī
    -0.07
     hinn
    -0.07
    Ñĥго
    -0.07
    åĬłæ¹¿
    -0.07
    andang
    -0.07
    ulette
    -0.07
     übern
    -0.07
    æ£ĢæŁ¥ç»Ħ
    -0.07
    POSITIVE LOGITS
    rod
    0.07
    patial
    0.07
    rest
    0.06
    oms
    0.06
    ç«ł
    0.06
     spatial
    0.06
    æĸİ
    0.06
    doors
    0.06
    以太
    0.06
    å¤Ń
    0.06
    Activations Density 0.002%

    No Known Activations