© 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. 3412
    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
    TexParameter
    -0.23
    >Main
    -0.22
     Flour
    -0.22
     sodom
    -0.21
    mlink
    -0.21
     *)((
    -0.20
    -span
    -0.20
    å¾Ģ
    -0.20
    :"#
    -0.20
    ç¾ķ
    -0.19
    POSITIVE LOGITS
    arseille
    0.20
    æijĦ
    0.19
     OnCollision
    0.19
    CDATA
    0.19
     OnTriggerEnter
    0.18
    iae
    0.18
    =pk
    0.18
    _LR
    0.18
    #####↵
    0.18
    çķĻå®Ī
    0.18
    Activations Density 0.000%

    No Known Activations