© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    Technical URLs

    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
     (!((
    -0.24
    antino
    -0.20
    åŬ
    -0.20
    å¾Ĺä¸įåĪ°
    -0.20
    ìĭ¶
    -0.19
    inline
    -0.19
    avanaugh
    -0.19
    æĥ¹
    -0.19
    æ°ij主çĶŁæ´»
    -0.19
    .borderWidth
    -0.19
    POSITIVE LOGITS
     piger
    0.25
    idency
    0.24
    :CGRect
    0.24
     HeaderComponent
    0.22
     ×Ķ×ķ×ĵ
    0.21
    )$_
    0.21
    +"<
    0.21
     Cougar
    0.20
     swingers
    0.20
     sacks
    0.19
    Activations Density 0.001%

    No Known Activations