© 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. 50113
    Prev
    Next
    INDEX
    Explanations

    new and original concepts

    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
    undler
    -0.08
    ched
    -0.07
    åĴĮç»´çĶŁç´ł
    -0.07
    åŁºæľ¬æĬĢèĥ½
    -0.07
    ULLET
    -0.07
     Erb
    -0.07
     rassegna
    -0.07
    urras
    -0.07
    éĻĪ家
    -0.07
    æľ¬åij½
    -0.07
    POSITIVE LOGITS
     new
    0.14
    /new
    0.12
    åħ¨æĸ°çļĦ
    0.12
     unique
    0.12
    new
    0.12
     novel
    0.12
    åħ¨æĸ°
    0.11
    unique
    0.11
    çĭ¬çī¹
    0.11
     mỼi
    0.11
    Activations Density 0.096%

    No Known Activations