© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    URL paths

    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
    ä¸įæĶ¹
    -0.08
    ocab
    -0.07
    çħ
    -0.07
    icer
    -0.07
    Âł
    -0.07
    áĢķáĢº
    -0.07
    åł
    -0.07
     Carroll
    -0.07
    æľīäºĶ
    -0.07
    å±Ĥå±Ĥ
    -0.07
    POSITIVE LOGITS
    riers
    0.07
    melden
    0.07
    izzes
    0.07
    .asc
    0.07
     ricer
    0.07
    èĤĥ
    0.07
    STA
    0.06
    ummings
    0.06
    жем
    0.06
    Įĵ
    0.06
    Activations Density 0.187%

    No Known Activations