© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    academic context

    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
    icester
    -0.22
    theid
    -0.21
    orsi
    -0.21
    TexParameter
    -0.21
    anoia
    -0.20
    ();)
    -0.20
    .toLocale
    -0.20
     briefed
    -0.20
    ','=',$
    -0.19
    æī¬
    -0.19
    POSITIVE LOGITS
    angstrom
    0.22
    åºĻ
    0.21
    orgeous
    0.20
    lage
    0.20
     Ruiz
    0.19
    och
    0.19
    outcome
    0.19
    é³Ķ
    0.18
    èī¾æ»ĭ
    0.18
    _SEG
    0.18
    Activations Density 0.001%

    No Known Activations