© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    sequences of repeating characters (zz, ww, SS, xxxxxxxx)2. numbers or alphanumeric sequences, often with repetition or specific lengths (4, 6, 1234a, 123456789)

    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
    klet
    -0.07
    inkel
    -0.07
    äºİäºĭ
    -0.07
    LETTE
    -0.06
    ovac
    -0.06
    çĶĺå¿ĥ
    -0.06
    winkel
    -0.06
    urv
    -0.06
    grave
    -0.06
    WithPath
    -0.06
    POSITIVE LOGITS
    echs
    0.07
    ãģĹãĤĤ
    0.07
    ÙĦات
    0.07
    bach
    0.07
    æĭīå¾·
    0.07
    itude
    0.06
     $('#'
    0.06
    riad
    0.06
    моÑĤ
    0.06
    /banner
    0.06
    Activations Density 0.046%

    No Known Activations