© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    evolved wells receptors peace

    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
    ees
    -0.07
    ness
    -0.06
    ists
    -0.06
     ones
    -0.06
     und
    -0.06
    еÑĤа
    -0.06
    ÑĤа
    -0.06
     hot
    -0.06
    tz
    -0.06
    ermann
    -0.06
    POSITIVE LOGITS
    uard
    0.08
    宾
    0.08
    è²Ķ
    0.08
    plice
    0.08
    èĨ¨
    0.08
    åŃ¦æľŁçļĦ
    0.08
    syl
    0.08
    笳
    0.07
    _sess
    0.07
    .rd
    0.07
    Activations Density 0.001%

    No Known Activations