© 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. 1995
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ç½ij游
    -0.20
    ðŁ¥ĩ
    -0.19
    æ´»è·ĥ
    -0.19
    .ListBox
    -0.19
    令çīĮ
    -0.18
    @AllArgsConstructor
    -0.18
     springfox
    -0.18
    以人为
    -0.18
    è¿Ļéĥ¨åĪĨ
    -0.18
    çİ°å®ŀçĶŁæ´»
    -0.18
    POSITIVE LOGITS
    leness
    0.28
    /Dk
    0.28
    itmap
    0.24
    ":[{↵
    0.23
    errals
    0.22
    endir
    0.22
    agements
    0.22
    ornment
    0.22
    OrElse
    0.22
    _$_
    0.21
    Activations Density 0.146%

    No Known Activations