© 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. 187
    Prev
    Next
    INDEX
    Explanations

    time duration

    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
     enthus
    -0.26
    usterity
    -0.23
    第ä¸ĢæŶéĹ´
    -0.22
    åıĸåĨ³
    -0.21
     ServiceException
    -0.21
    å¹´åĨħ
    -0.21
    èīı
    -0.20
    struments
    -0.20
    irlines
    -0.20
    æ§ĺãĢħ
    -0.19
    POSITIVE LOGITS
    -long
    0.33
     ago
    0.32
    /month
    0.30
     period
    0.27
    -old
    0.26
    -period
    0.26
    /year
    0.25
    polator
    0.24
    -ending
    0.24
    ration
    0.23
    Activations Density 2.942%

    No Known Activations