© 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. 61439
    Prev
    Next
    INDEX
    Explanations

    sum or fibonacci sequence

    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
    æĺŃ
    -0.08
    åįĥä¼ı
    -0.08
    å·¥åѦéĻ¢
    -0.08
     Olah
    -0.08
    andom
    -0.07
    :null
    -0.07
    ewa
    -0.07
    emun
    -0.07
    çĻ¾éĩĮ
    -0.07
    imate
    -0.07
    POSITIVE LOGITS
     sums
    0.08
     fibonacci
    0.07
    (sum
    0.06
     sum
    0.06
     births
    0.06
    sum
    0.06
     breeding
    0.06
    γεν
    0.06
     Fibonacci
    0.06
    -sum
    0.06
    Activations Density 0.007%

    No Known Activations