© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58970
    Prev
    Next
    INDEX
    Explanations

    mathematical sequence term

    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
    Negative Logits
    essen
    -0.09
    มั
    -0.07
    acro
    -0.06
    ji
    -0.06
    orna
    -0.06
    amente
    -0.06
    ente
    -0.06
    满身
    -0.06
    .c
    -0.06
    owo
    -0.06
    POSITIVE LOGITS
    ...',
    0.08
    åħ¨éĥ¨è¯Ħ论
    0.08
    -hide
    0.08
    âĢ¦]
    0.08
    ?}",
    0.08
    ãĢij,ãĢIJ
    0.08
    ...]
    0.07
     PROFE
    0.07
     Generation
    0.07
    __*/
    0.07
    Activations Density 0.051%

    No Known Activations