© 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. 708
    Prev
    Next
    INDEX
    Explanations

    of

    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
     --------------------------------------------------------------------------↵
    -0.21
    -placeholder
    -0.20
    ä¸Ģå®ļç¨ĭ度
    -0.19
    PRI
    -0.19
    vent
    -0.19
    .apiUrl
    -0.19
    åĬ¿
    -0.18
    ey
    -0.18
    |array
    -0.18
     xlink
    -0.18
    POSITIVE LOGITS
    @show
    0.26
    olist
    0.24
    ustomed
    0.23
    odiac
    0.23
    olkata
    0.23
    éļıæŶéļı
    0.22
     CDDL
    0.22
    微软éĽħé»ij
    0.22
    crast
    0.21
    èł²
    0.21
    Activations Density 0.819%

    No Known Activations