© 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. 2308
    Prev
    Next
    INDEX
    Explanations

    police searches and warrants

    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
    âŁ¹
    -0.24
    aten
    -0.21
    Mathf
    -0.20
    ç½ijç«Ļé¦ĸ页
    -0.19
    éĩį
    -0.19
    使çĶ¨èĢħæĪĸ
    -0.19
    .writeObject
    -0.18
    ãĤŃãĥ£
    -0.18
    çĽħ
    -0.18
    çĵ¿
    -0.18
    POSITIVE LOGITS
    rvine
    0.23
    lite
    0.23
    -cols
    0.23
    ç¡ķ士çłĶ究
    0.22
    ltra
    0.22
    .authorization
    0.21
     ]}↵
    0.21
    )))));↵
    0.21
    lijah
    0.21
    bservable
    0.21
    Activations Density 0.077%

    No Known Activations