© 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. 60027
    Prev
    Next
    INDEX
    Explanations

    number grouping or comparison

    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
    _PROC
    -0.09
    obiet
    -0.09
    _SCOPE
    -0.08
    icca
    -0.08
    缸åħ³èµĦ讯
    -0.08
    .getBytes
    -0.08
    Lexer
    -0.08
    ненко
    -0.08
     scopes
    -0.08
    кл
    -0.08
    POSITIVE LOGITS
    oul
    0.06
    æİĴ
    0.06
    RAP
    0.06
    _PD
    0.06
    æº
    0.06
    è½»
    0.06
    åĽ½
    0.06
    2
    0.06
     reb
    0.05
    _MP
    0.05
    Activations Density 0.045%

    No Known Activations