© 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. 61973
    Prev
    Next
    INDEX
    Explanations

    NOT true or wrong questions

    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
    æĸ©
    -0.08
    éĿłè°±
    -0.07
     mirac
    -0.07
    æĸ¬
    -0.06
    ennie
    -0.06
    ẢI
    -0.06
     else
    -0.06
    parcel
    -0.06
    ç§ī
    -0.06
    .types
    -0.06
    POSITIVE LOGITS
    à¸ļรร
    0.07
    æľīçĹħ
    0.07
    utore
    0.07
    æĪĸæľª
    0.07
    ¤íĮ
    0.07
    AKE
    0.07
    atcher
    0.07
    yto
    0.07
    çŀ©
    0.06
    à¸ĺิà¸ģาร
    0.06
    Activations Density 0.007%

    No Known Activations