© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    padding and spacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overseeing
    -0.10
    thers
    -0.10
    alth
    -0.10
    isan
    -0.09
    oom
    -0.09
    anos
    -0.09
     loose
    -0.09
    fur
    -0.09
    ork
    -0.09
     superv
    -0.09
    POSITIVE LOGITS
     deducted
    0.10
     subtract
    0.09
     shim
    0.09
     Ded
    0.09
    _zeros
    0.09
    (padding
    0.09
     deduction
    0.09
     subtraction
    0.08
    chen
    0.08
    .pb
    0.08
    Activations Density 0.231%

    No Known Activations