© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    With

    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
    ((__
    -0.24
     addCriterion
    -0.22
    (KeyCode
    -0.21
    mouseenter
    -0.20
    elmet
    -0.20
     slugg
    -0.20
    abei
    -0.20
    _vlan
    -0.20
    GetY
    -0.20
    ä¸įèĥ½ä¸ºç©º
    -0.19
    POSITIVE LOGITS
    æľīäºĨ
    0.25
    å¦ĤæѤ
    0.22
    }}},↵
    0.21
    InvalidArgumentException
    0.21
     regards
    0.21
    å·¥
    0.19
    è¿Ļä¹Ī
    0.19
    OLUMN
    0.19
     advent
    0.19
    egration
    0.19
    Activations Density 0.140%

    No Known Activations