© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    require/use

    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
    furt
    -0.21
    |=↵
    -0.20
    .EntityFramework
    -0.19
    ÃŃculo
    -0.19
     svenska
    -0.18
    å¿»
    -0.18
    eldorf
    -0.18
    écoute
    -0.18
    opération
    -0.18
    _KeyDown
    -0.18
    POSITIVE LOGITS
    éľĢè¦ģçĶ¨åĪ°
    0.42
     requiring
    0.40
     require
    0.35
    æ¶īåıĬ
    0.35
    requires
    0.34
     requires
    0.34
    éľĢè¦ģçĶ¨
    0.34
     needing
    0.34
    Uses
    0.33
     Requires
    0.33
    Activations Density 1.336%

    No Known Activations