© 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. 2118
    Prev
    Next
    INDEX
    Explanations

    know or familiar

    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
    ujet
    -0.26
    pekt
    -0.21
    opia
    -0.20
    arning
    -0.20
    æĦŁè§īèĩªå·±
    -0.19
    ä¸įæİĴéĻ¤
    -0.19
    uciones
    -0.19
    atty
    -0.19
     Geschäfts
    -0.18
    ogle
    -0.18
    POSITIVE LOGITS
     familiar
    0.49
    çĨŁæĤī
    0.42
    éĥ½çŁ¥éģĵ
    0.36
    çĨŁçŁ¥
    0.36
     Fam
    0.34
    çĨŁæĤīçļĦ
    0.34
    å°±çŁ¥éģĵ
    0.33
     know
    0.33
     familiarity
    0.33
    ä¹ŁçŁ¥éģĵ
    0.31
    Activations Density 0.510%

    No Known Activations