© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    amounts and doses

    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
     bureaucr
    -0.32
     disadv
    -0.30
     compañero
    -0.26
     Depths
    -0.26
     pione
    -0.25
     mogul
    -0.25
     dicks
    -0.25
    -leaning
    -0.24
     egreg
    -0.24
     lawmaker
    -0.24
    POSITIVE LOGITS
    avaÅŁ
    0.34
    %X
    0.33
    ðŁĺī
    0.32
    [".
    0.31
    ]={↵
    0.29
    ;set
    0.29
    agnar
    0.28
    %S
    0.28
    -DD
    0.27
    ayette
    0.27
    Activations Density 8.398%

    No Known Activations