© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8573
    Prev
    Next
    INDEX
    Explanations

    attributions and quotes

    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
    cul
    -0.09
     vein
    -0.08
    load
    -0.08
    acht
    -0.08
    amon
    -0.08
    UBE
    -0.08
     ved
    -0.07
    idas
    -0.07
    wed
    -0.07
    aho
    -0.07
    POSITIVE LOGITS
     according
    0.16
     says
    0.14
     said
    0.14
    according
    0.13
    says
    0.13
     According
    0.12
    said
    0.11
    According
    0.11
     Says
    0.10
     say
    0.10
    Activations Density 0.227%

    No Known Activations