© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61962
    Prev
    Next
    INDEX
    Explanations

    amine compounds

    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
    ToFit
    -0.08
    ãĥ«ãĤ¯
    -0.08
    ilee
    -0.08
    ä¸Ń磩
    -0.08
    ophobic
    -0.08
    çĥĺçĥ¤
    -0.08
    жела
    -0.07
    alow
    -0.07
    aldi
    -0.07
    ä»»æĢ¨
    -0.07
    POSITIVE LOGITS
    èĽ¾
    0.08
    欢è¿İ
    0.07
     عÙħ
    0.06
    oute
    0.06
    带åĽŀ
    0.06
     bÃły
    0.06
    adh
    0.06
    пÑĥ
    0.06
     reacts
    0.06
    .bind
    0.06
    Activations Density 0.008%

    No Known Activations