© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    extremely helpful

    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
    бол
    -0.06
    arrant
    -0.06
    æ²Ļ
    -0.06
    fo
    -0.06
    çľ
    -0.06
    åį§
    -0.06
    ress
    -0.06
    rew
    -0.06
    çĿ¡äºĨ
    -0.06
    uu
    -0.06
    POSITIVE LOGITS
    rake
    0.08
     consc
    0.08
    ãĥ¼ãĤ¯
    0.07
    ãĥ«ãĤ¯
    0.07
     Panas
    0.07
    æī§è¡Į人
    0.07
    alen
    0.07
    ارÙĩ
    0.07
     Eag
    0.07
    èĮĥåĦ¿
    0.07
    Activations Density 0.028%

    No Known Activations