© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    iteDatabase
    -0.24
    ")));
    -0.23
    '}}>
    -0.23
    Incre
    -0.21
    curacy
    -0.21
    .isNotBlank
    -0.20
    	Mono
    -0.20
    dre
    -0.20
    taken
    -0.20
    :request
    -0.20
    POSITIVE LOGITS
    äºİæѤ
    0.20
    stalk
    0.19
    æĹ¥åĨħ
    0.19
    |--------------------------------------------------------------------------↵
    0.18
    à¸ĩ
    0.18
     componentDidUpdate
    0.18
    ä¸ĭæīĭ
    0.18
    fty
    0.18
    isman
    0.18
    rops
    0.18
    Activations Density 0.001%

    No Known Activations