© 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. 44522
    Prev
    Next
    INDEX
    Explanations

    generated text

    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
     presently
    -0.07
    Pers
    -0.07
     demise
    -0.07
    对ä¸įèµ·
    -0.07
    elt
    -0.06
     accol
    -0.06
     Pers
    -0.06
    asal
    -0.06
     appropriately
    -0.06
    ahoo
    -0.06
    POSITIVE LOGITS
     please
    0.08
    æī¹æĶ¹
    0.08
    uos
    0.07
     inz
    0.07
    ×ķ×Ĵ
    0.07
    .gpu
    0.07
    åIJ¬å®Į
    0.07
    ica
    0.07
    teles
    0.07
    isci
    0.07
    Activations Density 0.014%

    No Known Activations