© 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. 2198
    Prev
    Next
    INDEX
    Explanations

    conditions and the following

    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
    ENER
    -0.09
    CONST
    -0.09
     bald
    -0.09
     Constit
    -0.09
    ular
    -0.09
     tal
    -0.08
    enthal
    -0.08
    DU
    -0.08
    eyJ
    -0.08
    icals
    -0.08
    POSITIVE LOGITS
    ifen
    0.08
    .vo
    0.08
     Curtain
    0.07
     Visibility
    0.07
    angan
    0.07
    oma
    0.07
    ited
    0.07
    /effects
    0.07
     Papers
    0.07
     satisf
    0.07
    Activations Density 0.052%

    No Known Activations