© 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. 3314
    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
    ourt
    -0.21
    acons
    -0.20
    ]=$
    -0.20
    tgl
    -0.20
    é»Ħæ²³
    -0.19
     }//
    -0.19
    adoo
    -0.19
    ******č↵
    -0.19
    igidbody
    -0.19
    .wind
    -0.19
    POSITIVE LOGITS
    Hôtel
    0.22
    è¯ķåį·
    0.22
     BaseEntity
    0.21
     (!((
    0.21
    èij¶
    0.20
    ober
    0.20
     CGRectGet
    0.20
    traî
    0.20
    entlich
    0.19
    zbek
    0.18
    Activations Density 0.000%

    No Known Activations