© 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. 165
    Prev
    Next
    INDEX
    Explanations

    null or zero

    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
    -UA
    -0.27
    -eslint
    -0.26
    -Compatible
    -0.26
    ={['
    -0.26
    褫
    -0.25
    :numel
    -0.25
    ————————————————
    -0.24
    ]--;↵
    -0.24
    ⾦
    -0.23
    )))));↵
    -0.22
    POSITIVE LOGITS
     zero
    0.59
     null
    0.46
    鼶
    0.43
    _zero
    0.43
    zero
    0.43
     None
    0.42
     Zero
    0.40
     nil
    0.40
    -zero
    0.39
     NULL
    0.39
    Activations Density 1.584%

    No Known Activations