© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    signal indication marker

    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
    },'
    -0.22
    aget
    -0.21
    bson
    -0.20
    æĹłéĻIJ
    -0.20
    .Addr
    -0.20
    (Equal
    -0.20
    .AutoComplete
    -0.20
    igth
    -0.19
    iev
    -0.19
    impan
    -0.19
    POSITIVE LOGITS
    æłĩå¿Ĺ
    0.39
    æłĩè¯Ĩ
    0.36
    ä¿¡åı·
    0.34
    æłĩè®°
    0.34
    è¯ĨåĪ«
    0.34
     signal
    0.31
     indication
    0.30
    æıIJéĨĴ
    0.29
    marker
    0.29
     indicator
    0.29
    Activations Density 0.715%

    No Known Activations