© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    code and names

    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
    ðŁĵIJ
    -0.26
    åĻĻ
    -0.25
    âľį
    -0.24
    ðŁijĨ
    -0.23
    íħį
    -0.23
    *)_
    -0.23
    FINE
    -0.23
    éĥħ
    -0.22
    LING
    -0.22
    -Semit
    -0.22
    POSITIVE LOGITS
    1
    0.23
    2
    0.23
    grily
    0.20
     cellForRowAtIndexPath
    0.20
     consolation
    0.20
    ä¸į解
    0.20
     granny
    0.20
    èµĦ
    0.19
    nonnull
    0.19
    ynthia
    0.19
    Activations Density 0.003%

    No Known Activations