© 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. 1836
    Prev
    Next
    INDEX
    Explanations

    asterisks

    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
     ApplicationException
    -0.33
    åĻĮ
    -0.30
     mastur
    -0.29
    çĿ¥
    -0.29
    #ga
    -0.27
    UILabel
    -0.27
     BusinessException
    -0.27
    笥
    -0.26
    窸
    -0.26
     homosex
    -0.26
    POSITIVE LOGITS
    erala
    0.32
    ocaly
    0.30
    ardu
    0.30
    ispens
    0.30
    ESSAGE
    0.30
    rray
    0.29
    amac
    0.29
    ornment
    0.27
    uminium
    0.27
    ;break
    0.27
    Activations Density 8.098%

    No Known Activations