© 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. 64170
    Prev
    Next
    INDEX
    Explanations

    cumulative sum or sequence numbers

    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
    smith
    -0.08
    æĮĿ
    -0.07
    åĮºåŁŁç»ıæµİ
    -0.07
     pun
    -0.07
    Curve
    -0.06
     Pun
    -0.06
    epak
    -0.06
     somme
    -0.06
     memb
    -0.06
    æľīèĩ´
    -0.06
    POSITIVE LOGITS
    è¿ľå¤§
    0.07
    éĢĹçķĻ
    0.07
     visit
    0.07
    çĴĥ
    0.07
    à¹Ģà¸ļืà¹īà¸Ńà¸ĩ
    0.07
    éģį
    0.07
    .npy
    0.07
     recurr
    0.07
     Hood
    0.07
    ucs
    0.06
    Activations Density 0.013%

    No Known Activations