© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    1
    -0.23
    å±ħ
    -0.20
    oten
    -0.20
    游æĪıå½ĵä¸Ń
    -0.20
     Palmer
    -0.18
    .subplots
    -0.18
    2
    -0.18
    rightness
    -0.18
    æĥĬ
    -0.18
    ernen
    -0.18
    POSITIVE LOGITS
    'options
    0.28
     èĩªåĬ¨çĶŁæĪIJ
    0.27
    IPHER
    0.23
    SURE
    0.22
    ":"/
    0.21
    åĨľè´¸
    0.21
    /Dk
    0.21
    lv
    0.20
    EDGE
    0.20
    'user
    0.20
    Activations Density 0.011%

    No Known Activations