© 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. 1207
    Prev
    Next
    INDEX
    Explanations

    errors and problems

    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
    })();↵↵
    -0.28
    ÑģÑĤолÑĮ
    -0.28
    åı¯æĥ³èĢĮ
    -0.25
    acades
    -0.24
    å±Ĥåĩºä¸į
    -0.24
    FTER
    -0.24
    licants
    -0.24
    byss
    -0.23
    >xpath
    -0.23
    -Semit
    -0.22
    POSITIVE LOGITS
    严éĩįçļĦ
    0.28
     prevention
    0.27
     gunman
    0.25
    -free
    0.24
    -resistant
    0.24
    累累
    0.24
    éĩįéĩį
    0.23
    çļĦåıijçĶŁ
    0.23
     Prevention
    0.23
    éĺ²æ²»
    0.23
    Activations Density 5.628%

    No Known Activations