© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    -
    -0.21
    å®ĥçļĦ
    -0.20
     useParams
    -0.20
    ä¸İåħ¶
    -0.20
     useHistory
    -0.20
     »↵↵
    -0.19
     Its
    -0.19
     lax
    -0.19
    =
    -0.18
     its
    -0.18
    POSITIVE LOGITS
     etc
    0.49
    etc
    0.48
     finally
    0.47
    çŃīçŃī
    0.45
    finally
    0.40
    çĶļèĩ³
    0.37
    çĶļèĩ³æĺ¯
    0.36
    æĢ»ä¹ĭ
    0.36
     even
    0.36
     Finally
    0.34
    Activations Density 2.112%

    No Known Activations