© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2737
    Prev
    Next
    INDEX
    Explanations

    play

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DbType
    -0.21
    åĶ³
    -0.19
     via
    -0.19
     refere
    -0.19
    _OWNER
    -0.19
    å¹¼
    -0.19
    	glVertex
    -0.18
    º
    -0.18
    çŁŃæļĤ
    -0.18
     adipisicing
    -0.18
    POSITIVE LOGITS
     ++;↵
    0.24
    é»ijæģ¶
    0.21
    /Peak
    0.21
    .getElementsByName
    0.20
    rigesimal
    0.20
    æĦł
    0.20
     cabo
    0.19
    ysqli
    0.19
    achen
    0.19
    ãĥµ
    0.19
    Activations Density 0.720%

    No Known Activations