© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
    åı¯æĥ³èĢĮ
    -0.27
    staking
    -0.23
    æĸ°æµªè´¢ç»ı
    -0.22
    .AdapterView
    -0.21
    qli
    -0.20
    ulerAngles
    -0.20
    çĬ¶
    -0.20
    ertiary
    -0.19
    RIX
    -0.19
     Bene
    -0.19
    POSITIVE LOGITS
    ä»»ä½ķ
    0.32
    ä¸įå¿ħè¦ģçļĦ
    0.30
    /min
    0.29
     any
    0.28
     unnecessary
    0.27
    ä»»ä½ķå½¢å¼ı
    0.27
    ä¸ĢåĪĩ
    0.26
     harmful
    0.24
    /mit
    0.24
    /remove
    0.23
    Activations Density 2.347%

    No Known Activations