© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    other

    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
    rello
    -0.19
    dorf
    -0.19
    endtime
    -0.18
    尤为éĩįè¦ģ
    -0.18
    çī¢è®°ä½¿åij½
    -0.18
    -dismiss
    -0.17
     bindActionCreators
    -0.17
    ?>č↵č↵
    -0.17
    "sync
    -0.17
    ichtig
    -0.17
    POSITIVE LOGITS
     other
    1.43
    åħ¶ä»ĸ
    1.40
    åħ¶å®ĥ
    1.34
    åħ¶ä»ĸçļĦ
    1.27
    other
    1.23
    Other
    1.03
     Other
    1.02
     OTHER
    1.01
    _other
    1.00
    åĪ«çļĦ
    0.99
    Activations Density 4.425%

    No Known Activations