© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    measurements and units

    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
     Kardash
    -0.28
     seedu
    -0.23
     Clintons
    -0.21
    esteem
    -0.21
    nyder
    -0.21
    ì·Ħ
    -0.21
    emploi
    -0.20
    mania
    -0.20
    dge
    -0.20
    NgModule
    -0.20
    POSITIVE LOGITS
    å·¦åı³
    0.43
    以åĨħ
    0.34
    以ä¸ĬçļĦ
    0.32
    eters
    0.25
     ago
    0.24
    ìĶ©
    0.23
    æ¾į
    0.23
    以ä¸Ĭ
    0.23
     worth
    0.22
    ChildIndex
    0.22
    Activations Density 2.181%

    No Known Activations