© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4294
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by common words

    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
     forms
    -0.08
     Forms
    -0.08
     pods
    -0.08
     Spl
    -0.07
     spl
    -0.07
    /form
    -0.07
     envision
    -0.07
    '
    -0.07
    rov
    -0.07
     segreg
    -0.07
    POSITIVE LOGITS
     Durant
    0.10
    hood
    0.10
    č↵↵
    0.09
    ebb
    0.09
    perature
    0.09
    its
    0.09
    urat
    0.09
    enting
    0.09
    ")]
    0.09
    @student
    0.09
    Activations Density 0.594%

    No Known Activations