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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 735
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    _AHB
    -0.23
     UIAlert
    -0.20
    碥
    -0.19
     c
    -0.18
    )throws
    -0.18
    对åħ¶çľŁå®ŀ
    -0.18
    è¿Ļ个èģĮä¸ļ
    -0.18
    åĴĤ
    -0.17
    å¾Ĺ太
    -0.17
    ëłµ
    -0.17
    POSITIVE LOGITS
     MediaTek
    0.24
    âĩĶ
    0.23
    QPushButton
    0.23
    çݩ家æľĭåıĭ
    0.23
    ".↵↵↵↵
    0.21
    .createSequentialGroup
    0.21
    -football
    0.21
    dehy
    0.21
    RouterModule
    0.21
    -Trump
    0.20
    Activations Density 0.119%

    No Known Activations