© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    section or group

    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
    cased
    -0.25
    linky
    -0.25
    -Semit
    -0.24
    )?$
    -0.24
    ,cp
    -0.23
    icorn
    -0.23
    ,readonly
    -0.22
    :expr
    -0.22
    berra
    -0.22
    !=(
    -0.21
    POSITIVE LOGITS
    (s
    0.24
    -wise
    0.22
    armacy
    0.20
    Âł
    0.20
    说åĪ°è¿ĻéĩĮ
    0.20
    åºĭ
    0.19
    éĽ³
    0.19
     ‘
    0.19
    çīĪæĿĥå½ĴåİŁ
    0.18
     RequestMethod
    0.18
    Activations Density 1.460%

    No Known Activations