© 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. 140
    Prev
    Next
    INDEX
    Explanations

    figures and tables

    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
    å¦Ĥ
    -0.21
    ä¿£
    -0.21
    è§ģ
    -0.21
    tones
    -0.20
    çĩİ
    -0.20
    hood
    -0.20
    è¦ĭ
    -0.19
    (MouseEvent
    -0.19
    berra
    -0.19
    ecast
    -0.19
    POSITIVE LOGITS
    )did
    0.28
    禳
    0.21
    abcdefghijklmnop
    0.21
    æīĢ示
    0.21
     Dank
    0.20
     gode
    0.20
    -middle
    0.19
    thinkable
    0.19
    ëĵľë¦¬
    0.19
    为æĬĵ
    0.19
    Activations Density 0.164%

    No Known Activations