© 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. 693
    Prev
    Next
    INDEX
    Explanations

    names/possessives

    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
    FormsModule
    -0.36
    /Dk
    -0.32
    :<?
    -0.28
    ingleton
    -0.26
    åı¯æĥ³èĢĮ
    -0.26
    #ga
    -0.26
    ÅĤat
    -0.25
    .SizeType
    -0.25
    ].'
    -0.25
    ácil
    -0.25
    POSITIVE LOGITS
    åIJį称
    0.30
    (s
    0.28
    's
    0.27
    _name
    0.24
    åĴĮæľįåĬ¡
    0.24
    let
    0.24
    lets
    0.24
     that
    0.22
    .
    0.22
    name
    0.22
    Activations Density 11.088%

    No Known Activations