© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    enables or helps

    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
    åıĹåĪ°äºĨ
    -0.27
     IOCTL
    -0.27
     disadv
    -0.25
    /mit
    -0.23
    ượ
    -0.23
    以人æ°ij为
    -0.22
    ä¸įåıĹ
    -0.22
    %;"
    -0.21
    éĩĩçĶ¨äºĨ
    -0.21
     intox
    -0.21
    POSITIVE LOGITS
    使
    0.49
    使å¾Ĺ
    0.46
    导èĩ´
    0.39
     enable
    0.38
     allows
    0.37
     help
    0.36
     allow
    0.36
    使åħ¶
    0.36
     enables
    0.35
     helps
    0.35
    Activations Density 4.336%

    No Known Activations