© 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. 616
    Prev
    Next
    INDEX
    Explanations

    here

    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
    ;base
    -0.26
    )?$
    -0.25
    'class
    -0.25
    ;o
    -0.25
    seau
    -0.24
    mö
    -0.24
    *num
    -0.23
    ungeons
    -0.23
    >manual
    -0.23
     zoekt
    -0.23
    POSITIVE LOGITS
    after
    0.34
    abouts
    0.33
    für
    0.28
    -même
    0.25
    upon
    0.24
    roperties
    0.23
     ÙĪÙĩÙĨاÙĥ
    0.22
    ìĦľ
    0.22
    uforia
    0.21
    unto
    0.21
    Activations Density 0.657%

    No Known Activations