© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    citations or links

    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
    *dt
    -0.26
    matchCondition
    -0.25
    *pow
    -0.22
    :'.$
    -0.22
    åºĭ
    -0.21
    éĵ¨
    -0.21
     =>'
    -0.21
    IED
    -0.20
    /fwlink
    -0.20
    }_${
    -0.20
    POSITIVE LOGITS
    alez
    0.21
     newX
    0.21
    ummings
    0.21
    bellion
    0.18
    PG
    0.18
    ',{↵
    0.18
    _WRONG
    0.18
    çļĦæķĪæŀľ
    0.18
    ocaly
    0.18
    urse
    0.18
    Activations Density 0.029%

    No Known Activations