© 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. 42305
    Prev
    Next
    INDEX
    Explanations

    time and space travel

    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
     compresi
    -0.08
    éķ¿ç©º
    -0.08
    çŤ
    -0.07
     Postar
    -0.07
    åħ±åIJĮåıĤä¸İ
    -0.07
    atoon
    -0.07
     krop
    -0.07
    etahui
    -0.07
    çĬ¶åħĥ
    -0.07
    åįģåĪĨéĩįè¦ģ
    -0.07
    POSITIVE LOGITS
    åı¯è¡Į
    0.08
    åı¯è¡ĮçļĦ
    0.08
    avel
    0.07
    åı¯è¡ĮæĢ§
    0.07
     mathematics
    0.07
    å¾Ģè¿Ķ
    0.07
     spac
    0.07
    åı¯èĥ½æĢ§
    0.07
    åħ¬çĦ¶
    0.07
    çĪ±å¾·åįİ
    0.07
    Activations Density 0.008%

    No Known Activations