© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4904
    Prev
    Next
    INDEX
    Explanations

    filename suffixes and identifiers

    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
    Negative Logits
    owell
    -0.09
    ebles
    -0.09
    èĴĤæĸ¯
    -0.08
    æ²ĥæĸ¯
    -0.08
    ooks
    -0.08
    schlag
    -0.08
    oke
    -0.08
    eble
    -0.08
    érie
    -0.07
    ç»´å°Ķ
    -0.07
    POSITIVE LOGITS
    umba
    0.07
    æ°§åĮĸ碳
    0.07
    bag
    0.06
    ly
    0.06
    ewa
    0.06
    eware
    0.06
    maq
    0.06
    lay
    0.06
    ëħĢ
    0.06
    à¸Ńัà¸Ļ
    0.06
    Activations Density 0.077%

    No Known Activations