© 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. 1124
    Prev
    Next
    INDEX
    Explanations

    numbers and prices

    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
    eron
    -0.26
    檬
    -0.20
     cé
    -0.20
    ç³ĸå°¿
    -0.19
    西æ¹ĸ
    -0.19
    OrFail
    -0.19
    å°¾
    -0.19
    羶
    -0.19
    åĮħåĮħ
    -0.18
     });↵↵↵↵
    -0.18
    POSITIVE LOGITS
    orgetown
    0.25
    ±ħ
    0.23
    estruction
    0.20
    	explicit
    0.19
    QRS
    0.19
    intree
    0.19
    ·¸
    0.19
    :numel
    0.19
    éĢłæŀĹ
    0.19
    .inflate
    0.18
    Activations Density 0.718%

    No Known Activations