© 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. 1195
    Prev
    Next
    INDEX
    Explanations

    compounds or mysteries

    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
    尼奥
    -0.08
    /std
    -0.07
    owitz
    -0.07
    stig
    -0.07
    æĹłäºĭ
    -0.07
    Cipher
    -0.07
    OMPI
    -0.07
    eloos
    -0.07
    åħĦ妹
    -0.07
    RequestId
    -0.07
    POSITIVE LOGITS
    æľªçŁ¥
    0.07
     unknown
    0.07
    alte
    0.07
    ä¸İåĽ½å®¶
    0.07
     whatever
    0.07
    è¦ģåĴĮ
    0.07
     Unknown
    0.07
    åĴĮæĪijä¸Ģèµ·
    0.07
    åħģ
    0.06
    æĹłåIJį
    0.06
    Activations Density 0.106%

    No Known Activations