© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    hidden

    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
    )((((
    -0.31
    âļĹ
    -0.30
    entiful
    -0.29
    :<?
    -0.29
    ='<?
    -0.28
    },{↵
    -0.28
    iffany
    -0.28
    @dynamic
    -0.28
     newcom
    -0.28
    ëĸĦ
    -0.27
    POSITIVE LOGITS
     hiding
    0.39
     hidden
    0.38
    éļIJèĹı
    0.36
    èĹı
    0.36
    åĮ¿
    0.35
    èĹıçĿĢ
    0.35
    éļIJ
    0.35
     behind
    0.34
    hidden
    0.34
    (hidden
    0.33
    Activations Density 0.402%

    No Known Activations