© 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. 2829
    Prev
    Next
    INDEX
    Explanations

    procedures and methods

    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
    ì¼Ģ
    -0.19
    )=='
    -0.18
    .SelectedItems
    -0.18
    ([]);↵↵
    -0.18
     preliminary
    -0.18
     heightFor
    -0.18
     cellForRowAt
    -0.18
    .getBoundingClientRect
    -0.18
    odel
    -0.18
    >');↵↵
    -0.17
    POSITIVE LOGITS
    anean
    0.24
    @ResponseBody
    0.22
    деÑģÑĮ
    0.21
     ('$
    0.21
    STRUCTIONS
    0.21
    openh
    0.20
    _variation
    0.20
    .sponge
    0.19
    onio
    0.19
    #Region
    0.19
    Activations Density 0.077%

    No Known Activations