© 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. 2055
    Prev
    Next
    INDEX
    Explanations

    triple quotes

    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
     (;;)
    -0.26
    âĻĤ
    -0.22
    SURE
    -0.20
     âĻ¥
    -0.20
    |RF
    -0.20
     fkk
    -0.20
    ï¹ģ
    -0.19
    HELP
    -0.19
    asename
    -0.19
     CircularProgress
    -0.19
    POSITIVE LOGITS
    å¾ľ
    0.23
    buat
    0.22
     disg
    0.20
     Attr
    0.19
    ç»Į
    0.19
    annah
    0.19
    deprecated
    0.19
    kü
    0.19
    convertView
    0.19
    lrt
    0.18
    Activations Density 0.026%

    No Known Activations