© 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. 54054
    Prev
    Next
    INDEX
    Explanations

    special character separators

    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
    ä¾
    -0.10
    Peace
    -0.10
    anja
    -0.10
    esus
    -0.09
     Peace
    -0.09
     advant
    -0.09
    odiac
    -0.09
     ROOT
    -0.09
    orthand
    -0.09
    .dev
    -0.09
    POSITIVE LOGITS
     Norton
    0.08
     cross
    0.08
    anz
    0.07
    /apt
    0.07
     crossed
    0.07
    ai
    0.07
     tym
    0.07
    atal
    0.07
     Bat
    0.07
    raz
    0.07
    Activations Density 0.004%

    No Known Activations