© 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. 984
    Prev
    Next
    INDEX
    Explanations

    time ago

    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
    psilon
    -0.10
     hers
    -0.10
     always
    -0.10
    eri
    -0.09
     never
    -0.09
     tomorrow
    -0.09
     неÑĤ
    -0.09
    always
    -0.09
    itori
    -0.09
    eyed
    -0.09
    POSITIVE LOGITS
    when
    0.10
     amidst
    0.09
     when
    0.09
    (after
    0.09
    -begin
    0.09
     onwards
    0.09
     began
    0.09
     tragedy
    0.09
     realizing
    0.09
    å¼Ģå§ĭ
    0.09
    Activations Density 1.194%

    No Known Activations