© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4277
    Prev
    Next
    INDEX
    Explanations

    package manager output

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ><?
    -0.28
    (DbContext
    -0.23
    ä¸ĢåįĬ
    -0.19
    éĵ²
    -0.19
    å¾ģ
    -0.19
     half
    -0.19
    }/#{
    -0.19
    PickerController
    -0.18
    .Unmarshal
    -0.18
    	GLuint
    -0.18
    POSITIVE LOGITS
    .statusText
    0.24
    stdexcept
    0.23
    %);↵
    0.23
    .VisualBasic
    0.22
    nage
    0.21
     }};↵
    0.21
    ibaba
    0.21
    è§
    0.20
    ç®
    0.20
    ?family
    0.19
    Activations Density 0.192%

    No Known Activations