© 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. 286
    Prev
    Next
    INDEX
    Explanations

    technical or legal documentation

    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
    .Comparator
    -0.32
     cuckold
    -0.31
    ampie
    -0.31
    odesk
    -0.30
    ogenerated
    -0.30
    ytt
    -0.29
    ignet
    -0.28
    imary
    -0.26
    ceries
    -0.26
    forgettable
    -0.26
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.24
    âĻĤ
    0.21
    *);↵↵
    0.21
     èĩªåĬ¨çĶŁæĪIJ
    0.20
    ´
    0.20
    åĸ¹
    0.20
     bevor
    0.20
    .addTarget
    0.20
    ä½Ĩä¸įéĻIJäºİ
    0.20
    IONS
    0.20
    Activations Density 2.948%

    No Known Activations