© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    chemical elements/compounds

    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
    @testable
    -0.24
     @"\
    -0.23
     LENG
    -0.23
     FixedUpdate
    -0.23
    ç¿Ģ
    -0.22
    -style
    -0.21
    éºĩ
    -0.21
    orgetown
    -0.21
    .Logf
    -0.21
    CCCCCC
    -0.20
    POSITIVE LOGITS
    åIJ«éĩı
    0.30
    :host
    0.25
    -svg
    0.25
    __':č↵
    0.24
    .rmi
    0.22
     adulti
    0.21
     zwarte
    0.21
     content
    0.21
     *);↵↵
    0.20
    å®ŀäºĭæ±Ĥ
    0.20
    Activations Density 4.843%

    No Known Activations