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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3411
    Prev
    Next
    INDEX
    Explanations

    say "in" or "to"

    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
     beÄŁen
    -0.21
     inne
    -0.20
    .initState
    -0.19
    evice
    -0.19
    __':↵
    -0.19
    'icon
    -0.19
    íĶĦë¡ľê·¸
    -0.19
    ipherals
    -0.19
     onBind
    -0.19
    POSITIVE LOGITS
     onto
    0.41
    onto
    0.38
     into
    0.35
     Into
    0.33
    Into
    0.30
    into
    0.30
    _into
    0.29
     INTO
    0.28
    .into
    0.23
    \OptionsResolver
    0.22
    Activations Density 0.718%

    No Known Activations