© 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. 46190
    Prev
    Next
    INDEX
    Explanations

    legal and important concepts

    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
     demean
    -0.08
    æľĢæĸ°ç«łèĬĤ
    -0.07
    /fw
    -0.07
    å¢Ł
    -0.07
    —the
    -0.07
    è³Ľ
    -0.07
    cek
    -0.07
    åħ¶è§ĤçĤ¹
    -0.07
    å¤Ħå¤Ħ
    -0.07
     repeated
    -0.07
    POSITIVE LOGITS
    alus
    0.07
    oras
    0.07
    注æĺİçļĦ
    0.07
    pek
    0.07
    å¦ĤæĦ¿
    0.07
    çĦ¶èĢĮåľ¨
    0.06
    lass
    0.06
    ç½ķè§ģçļĦ
    0.06
    ç½ķè§ģ
    0.06
    arkan
    0.06
    Activations Density 0.001%

    No Known Activations