© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    code modules

    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
    libft
    -0.27
    OffsetTable
    -0.24
     ×Ķ×ķ×ĵ
    -0.23
    -caret
    -0.23
    "description
    -0.21
    igator
    -0.21
    -toast
    -0.21
    -translate
    -0.21
    .getSeconds
    -0.21
    UCCESS
    -0.21
    POSITIVE LOGITS
    èģĶ绾
    0.22
     hvor
    0.19
    ıy
    0.19
    ins
    0.18
    éĺµ
    0.18
    å®¡æŁ¥
    0.18
     DEALINGS
    0.18
     Relief
    0.18
    认åIJĮ
    0.17
    áºı
    0.17
    Activations Density 0.001%

    No Known Activations