© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    Journal abbreviations

    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
    VERRIDE
    -0.30
    'icon
    -0.28
    )index
    -0.28
    :".$
    -0.28
    )?$
    -0.27
     salopes
    -0.26
    bove
    -0.26
    ¡´
    -0.25
    'options
    -0.24
    :both
    -0.24
    POSITIVE LOGITS
     vol
    0.22
    bufio
    0.21
     "");
    0.20
    uintptr
    0.20
    æĿĤå¿Ĺ
    0.20
     research
    0.20
     SWAT
    0.19
     ReactiveFormsModule
    0.19
     },↵↵↵
    0.19
     typingsJapgolly
    0.19
    Activations Density 0.440%

    No Known Activations