© 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. 55005
    Prev
    Next
    INDEX
    Explanations

    left or right side

    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
    AtPath
    -0.08
    æ®ĩ
    -0.08
    hyl
    -0.08
     myriad
    -0.08
    æĬ
    -0.08
    æ¿
    -0.08
     punc
    -0.07
    utang
    -0.07
    WithOptions
    -0.07
    gados
    -0.07
    POSITIVE LOGITS
    æĮĩå®ļçļĦ
    0.07
     Pil
    0.06
    就该
    0.06
    ueb
    0.06
    mov
    0.06
     adjacent
    0.06
     manc
    0.06
    çħ§çĿĢ
    0.06
     inferred
    0.06
    Æ°a
    0.06
    Activations Density 0.009%

    No Known Activations