© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    d-wave ligands

    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
    macher
    -0.08
    尼迪
    -0.08
    methode
    -0.07
    èIJ½èIJ½
    -0.07
    è¡¡
    -0.07
    .lift
    -0.07
    Äĵr
    -0.07
    à¹ģหà¹Īà¸ĩ
    -0.07
     microf
    -0.07
    注åĨĮçļĦ
    -0.07
    POSITIVE LOGITS
    inki
    0.08
    縼
    0.07
    Shield
    0.07
    еÑĩениÑı
    0.07
     shut
    0.06
    解ç¦ģ
    0.06
    æŁ¥çľĭåħ¨éĥ¨
    0.06
    åĽļ
    0.06
    ruhe
    0.06
     chemistry
    0.06
    Activations Density 0.001%

    No Known Activations