© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    threshold value

    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
     typingsSlinky
    -0.25
     typingsJapgolly
    -0.24
    ):?>↵
    -0.24
     potrÃł
    -0.21
    /Dk
    -0.21
     averages
    -0.20
    èµĤ
    -0.20
    ;\">
    -0.19
    æĹ¶ä»£ä¸ŃåĽ½
    -0.19
    âĬ¿
    -0.18
    POSITIVE LOGITS
     threshold
    0.25
    threshold
    0.24
    ollider
    0.23
     Threshold
    0.22
    Criterion
    0.21
    vably
    0.21
    inidad
    0.21
    -bold
    0.21
    paginator
    0.20
    _threshold
    0.20
    Activations Density 0.021%

    No Known Activations