© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    legal clauses and requirements

    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
     barely
    -0.10
     almost
    -0.10
     supposedly
    -0.09
     somehow
    -0.09
     unfortunately
    -0.09
     (~
    -0.09
     worth
    -0.09
     somewhere
    -0.08
     dramatically
    -0.08
     tweak
    -0.08
    POSITIVE LOGITS
     shall
    0.19
     Shall
    0.15
    shall
    0.14
     any
    0.14
     hereby
    0.14
     notwithstanding
    0.13
    soever
    0.13
     subject
    0.13
     specified
    0.12
     SHALL
    0.12
    Activations Density 0.959%

    No Known Activations