© 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. 260
    Prev
    Next
    INDEX
    Explanations

    remove

    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
    ä¸įä¸Ĭ
    -0.22
    IALOG
    -0.21
     erotica
    -0.19
    ока
    -0.19
    åī¯åİ¿éķ¿
    -0.19
    åĪ°æĿ¥
    -0.19
     Inputs
    -0.18
    FLICT
    -0.18
    "crypto
    -0.18
    ASHBOARD
    -0.18
    POSITIVE LOGITS
     khá»ıi
    0.48
    æİī
    0.38
    æİīäºĨ
    0.32
    ponge
    0.27
    apest
    0.26
    osemite
    0.26
    ribly
    0.25
    -unused
    0.25
    omal
    0.25
    rvine
    0.24
    Activations Density 3.379%

    No Known Activations