© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    same or simple

    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
     },{
    -0.23
     (!((
    -0.22
     mktime
    -0.21
    Incomplete
    -0.21
    _NT
    -0.21
    ilos
    -0.20
     YaÅŁ
    -0.20
    :@""
    -0.20
    -Compatible
    -0.20
    inality
    -0.20
    POSITIVE LOGITS
     trivial
    0.34
     identical
    0.34
     equal
    0.28
     coinc
    0.28
     simpl
    0.27
    ç®ĢåĮĸ
    0.27
    çŃīäºİ
    0.27
     Simpl
    0.26
     coincide
    0.24
    åįķä¸Ģ
    0.24
    Activations Density 0.167%

    No Known Activations