© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3174
    Prev
    Next
    INDEX
    Explanations

    speaking or reporting

    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
    &id
    -0.23
    /Dk
    -0.23
    _ptrs
    -0.21
    ervals
    -0.21
    mont
    -0.20
    ILED
    -0.20
     proposé
    -0.20
    avigate
    -0.20
    æľīçļĦçݩ家
    -0.19
    æĹıèĩªæ²»å·ŀ
    -0.19
    POSITIVE LOGITS
     publicly
    0.34
     public
    0.25
    åħ¬å¼Ģ
    0.24
    对å¤ĸ
    0.23
    public
    0.23
    åIJ¦è®¤
    0.22
    åľ¨æİ¥åıĹ
    0.22
     púb
    0.22
    称
    0.21
    -public
    0.21
    Activations Density 0.507%

    No Known Activations