© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
    pass
    -0.20
    å®ģéĿĻ
    -0.20
     onBind
    -0.20
     umo
    -0.18
    s
    -0.18
     actionTypes
    -0.18
    achuset
    -0.18
    awaiter
    -0.18
    _datos
    -0.18
    le
    -0.18
    POSITIVE LOGITS
     dequeueReusableCellWithIdentifier
    0.26
    -Semit
    0.25
    :';↵
    0.25
     cuckold
    0.25
    çıµ
    0.25
    /tos
    0.25
    /Branch
    0.25
    çij¨
    0.25
    '/>
    0.24
    çij¢
    0.24
    Activations Density 1.157%

    No Known Activations