© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    previously mentioned or referred to above

    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
    .El
    -0.09
    aina
    -0.09
    elin
    -0.09
    ault
    -0.09
    ampp
    -0.08
    apest
    -0.08
     blanc
    -0.08
    éĢ£
    -0.08
    ark
    -0.08
    ä¸ĭ
    -0.08
    POSITIVE LOGITS
     aforementioned
    0.38
     above
    0.33
    above
    0.28
     mentioned
    0.25
     afore
    0.25
    mentioned
    0.21
     Above
    0.21
     ABOVE
    0.21
     foregoing
    0.20
    以ä¸Ĭ
    0.20
    Activations Density 1.471%

    No Known Activations