© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2375
    Prev
    Next
    INDEX
    Explanations

    code and definitions

    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
    ={['
    -0.27
    -Identifier
    -0.26
    #ga
    -0.25
    estruction
    -0.25
    {}{↵
    -0.24
    OutOfRangeException
    -0.24
    #aa
    -0.23
    unkt
    -0.23
    VERTISE
    -0.23
    VERN
    -0.23
    POSITIVE LOGITS
    èĨ³
    0.22
    è£Ķ
    0.21
    _UNS
    0.20
    ier
    0.20
    loc
    0.19
    æŃ£éĿ¢
    0.19
    U
    0.19
    ÙĤÙĬÙĦ
    0.19
     predecess
    0.18
    conexao
    0.18
    Activations Density 0.001%

    No Known Activations