© 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. 3006
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .YELLOW
    -0.21
    aria
    -0.21
     Rebel
    -0.20
     WHATSOEVER
    -0.20
     endforeach
    -0.19
     \''
    -0.18
    antis
    -0.18
     Summon
    -0.18
    建åįİ
    -0.18
    _baseline
    -0.18
    POSITIVE LOGITS
    'icon
    0.25
     helicopt
    0.22
    ç½Ķ
    0.22
    autorelease
    0.21
     misd
    0.21
    traî
    0.20
    orsche
    0.20
    -cn
    0.20
    interpre
    0.19
    abd
    0.19
    Activations Density 0.000%

    No Known Activations