© 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. 51963
    Prev
    Next
    INDEX
    Explanations

    prefixes of code 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
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.06
     Ingl
    -0.06
    (True
    -0.06
    ()
    -0.05
    ebro
    -0.05
    ¿
    -0.05
    -0.05
    **
    -0.05
    ève
    -0.05
    ÛIJ
    -0.05
    POSITIVE LOGITS
    opedia
    0.09
    anaf
    0.09
    ertools
    0.08
    plib
    0.08
    rnd
    0.08
    ntax
    0.08
     -**
    0.08
    کت
    0.08
    åħ³äºİåģļ好
    0.08
    วà¸ģ
    0.08
    Activations Density 0.248%

    No Known Activations