© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    1

    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
    æħij
    -0.21
    NZ
    -0.20
    åľ°ä¸Ĭ
    -0.18
     [][]
    -0.18
     R
    -0.18
    åĨ
    -0.18
     ser
    -0.18
    çİij
    -0.18
    son
    -0.18
    ining
    -0.18
    POSITIVE LOGITS
    çĽijåIJ¬é¡µéĿ¢
    0.26
    ë³į
    0.26
     DataGridViewCellStyle
    0.26
     Escorts
    0.25
     buc
    0.25
    æľīçļĦçݩ家
    0.24
    berra
    0.24
    $LANG
    0.24
     addCriterion
    0.24
     fucks
    0.24
    Activations Density 0.398%

    No Known Activations