© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    (

    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
    bases
    -0.20
     Million
    -0.20
    åŃĹ第
    -0.19
    à¸Ħà¸Ńม
    -0.18
    èĵĩ
    -0.18
    (errno
    -0.18
    ’T
    -0.18
    xfb
    -0.18
    	pthread
    -0.18
    éĽĩ
    -0.17
    POSITIVE LOGITS
    âļĹ
    0.30
    åĿļå®ļä¸į
    0.25
    ðŁĵIJ
    0.25
    ;br
    0.23
    åij£
    0.23
    @Web
    0.23
    asurer
    0.23
     HOLDER
    0.23
    dziaÅĤ
    0.22
    eggies
    0.22
    Activations Density 0.217%

    No Known Activations