© 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. 56150
    Prev
    Next
    INDEX
    Explanations

    negotiate, negotiations, negotiators

    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
    agas
    -0.08
    atic
    -0.08
     fore
    -0.07
    ality
    -0.07
    ulo
    -0.07
    IDA
    -0.07
    erton
    -0.07
     engineered
    -0.07
    FileChooser
    -0.07
    tee
    -0.07
    POSITIVE LOGITS
    ABLE
    0.11
     proper
    0.10
    lass
    0.10
    åĥ
    0.09
    ê
    0.09
    ubes
    0.09
    lemma
    0.09
     skills
    0.09
    izable
    0.09
    -la
    0.09
    Activations Density 0.006%

    No Known Activations