© 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. 1128
    Prev
    Next
    INDEX
    Explanations

    |

    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
    abcdefghijkl
    -0.28
    indsight
    -0.27
    窸
    -0.24
    ABCDEFGHIJKLMNOP
    -0.23
    abcdefghijklmnop
    -0.23
    róż
    -0.23
    丫头
    -0.23
    dere
    -0.21
    errated
    -0.21
    تÙĪج
    -0.21
    POSITIVE LOGITS
    _HERSHEY
    0.23
    ï¬Ħ
    0.22
    alleries
    0.22
    <stdlib
    0.22
    	mysqli
    0.21
    ä¸ĭéĿ¢æĺ¯å°ı
    0.21
    exels
    0.21
    esan
    0.21
    коло
    0.20
     GdaÅĦsk
    0.20
    Activations Density 0.162%

    No Known Activations