© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    how many pathswhat is the remainderwhat are the prime factorswhat is the second derivativewhat is the remainderwhat is p(w(y))what is z(n(u))what is w rounded to 1 decimal placewhat is the maximum speed

    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
    otá
    -0.09
    æv
    -0.09
    ("'"
    -0.08
    getTable
    -0.08
    anders
    -0.08
    utr
    -0.08
    inson
    -0.08
    绣
    -0.08
    jeti
    -0.07
    veen
    -0.07
    POSITIVE LOGITS
    äºı
    0.06
    寥
    0.06
       ↵
    0.06
    èĻ§
    0.05
    åıįåºĶçļĦ
    0.05
     patter
    0.05
     span
    0.05
     Gord
    0.05
     sufficient
    0.05
     nevertheless
    0.05
    Activations Density 0.090%

    No Known Activations