© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 995
    Prev
    Next
    INDEX
    Explanations

    [@

    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
    .EndsWith
    -0.26
    ]?.
    -0.22
     saldo
    -0.22
    _RM
    -0.20
    anke
    -0.19
    è¯Į
    -0.19
    .RadioButton
    -0.19
    æĦŁäºº
    -0.19
    ån
    -0.18
     coraz
    -0.18
    POSITIVE LOGITS
    crast
    0.26
    ÐļÑĥпиÑĤÑĮ
    0.24
     Noticed
    0.23
     endors
    0.22
    atég
    0.21
     CascadeType
    0.21
    pone
    0.21
    utow
    0.21
    oggler
    0.20
    prar
    0.20
    Activations Density 1.118%

    No Known Activations