© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1797
    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
     novitÃł
    -0.22
     neger
    -0.22
    æľīæľŁ
    -0.21
     qualitÃł
    -0.21
     Decomp
    -0.20
    åħĭæľį
    -0.20
    ãĤĴè¶ħãģĪ
    -0.20
    nants
    -0.20
    andidates
    -0.20
    HORT
    -0.20
    POSITIVE LOGITS
    CompleteListener
    0.24
    年产
    0.20
    APPER
    0.20
    ä¸ĭéĿ¢æĺ¯å°ı
    0.19
     punches
    0.19
    acher
    0.19
    @Entity
    0.19
    ">&#
    0.19
    åĥĩ
    0.18
     contr
    0.18
    Activations Density 0.000%

    No Known Activations