© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    presence or absence

    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
     ëĭ¤ë§Į
    -0.20
    å¤įæŁ¥
    -0.20
     }])↵
    -0.19
    ãĥµ
    -0.18
    ération
    -0.18
    è§ij
    -0.18
    uttle
    -0.18
    (COLOR
    -0.18
    inkle
    -0.18
    æĺ¶
    -0.18
    POSITIVE LOGITS
     presence
    0.31
     having
    0.29
    æľīäºĨ
    0.28
    æŃ¤ä¸¾
    0.28
     absence
    0.25
    having
    0.25
    presence
    0.24
     combination
    0.24
    ä¸ĢæŦ
    0.24
     Having
    0.23
    Activations Density 0.791%

    No Known Activations