© 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. 3119
    Prev
    Next
    INDEX
    Explanations

    specific names or titles

    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
    -Compatible
    -0.26
     libertin
    -0.24
    :CGRect
    -0.24
    /Runtime
    -0.21
     Millenn
    -0.21
     Jackets
    -0.21
    OLON
    -0.21
     }])↵
    -0.21
    )./
    -0.20
     fkk
    -0.20
    POSITIVE LOGITS
    ([]*
    0.19
    åħįè´£
    0.18
    inke
    0.18
     Rem
    0.18
    éĥijéĩį
    0.18
     <->
    0.18
     teg
    0.18
    bow
    0.18
    importe
    0.18
     prive
    0.18
    Activations Density 0.010%

    No Known Activations