© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29049
    Prev
    Next
    INDEX
    Explanations

    propose methods, assumptions, are

    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
    Ä«ts
    -0.08
    好å¤ļ
    -0.08
    åı¯éĢīä¸Ń
    -0.08
     varios
    -0.07
     vários
    -0.07
    .Sys
    -0.07
     óp
    -0.07
     Several
    -0.07
    Ñĩиком
    -0.07
    ä¸īéĩį
    -0.07
    POSITIVE LOGITS
    çļĦ两个
    0.11
     two
    0.10
    åĪĨåĪ«æĺ¯
    0.10
    -two
    0.09
    two
    0.09
    åĪĨåĪ«ä¸º
    0.09
    è¿Ļ两个
    0.09
     Two
    0.09
    Two
    0.08
     altrett
    0.08
    Activations Density 0.084%

    No Known Activations