© 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. 10397
    Prev
    Next
    INDEX
    Explanations

    histogram and bin

    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
    ild
    -0.07
    ibil
    -0.07
    urai
    -0.07
    ÑĥÑĢе
    -0.07
    çºł
    -0.07
    üng
    -0.06
    Ïĩο
    -0.06
    ĴĪ
    -0.06
    åĪ°æĤ¨çļĦ
    -0.06
    æ¡ĪåĨħ
    -0.06
    POSITIVE LOGITS
    å½Ĵ
    0.08
    é¦Ļå±±
    0.08
    alize
    0.08
    ingu
    0.07
    代表
    0.07
    _normalize
    0.07
    宽
    0.07
    大éģĵ
    0.07
     Loved
    0.07
     normalization
    0.07
    Activations Density 0.036%

    No Known Activations