© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    versions

    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
    phants
    -0.25
    踽
    -0.25
    ))==
    -0.23
    åıĪ好åıĪ
    -0.21
    .scalablytyped
    -0.21
    说çļĦæĺ¯
    -0.20
    .AppendFormat
    -0.20
    uguay
    -0.20
    anship
    -0.20
    -Allow
    -0.19
    POSITIVE LOGITS
    çīĪæľ¬
    0.25
     versions
    0.24
     thereof
    0.24
    versions
    0.21
    toArray
    0.21
    ircraft
    0.20
    isations
    0.20
    irlines
    0.20
     version
    0.20
    ÊĴ
    0.19
    Activations Density 0.652%

    No Known Activations