© 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. 61537
    Prev
    Next
    INDEX
    Explanations

    $\langle$ followed by symbols

    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
    Ñĩ
    -0.09
    _bs
    -0.09
    bon
    -0.08
    dy
    -0.08
    ently
    -0.08
    ож
    -0.08
    ally
    -0.07
     Hide
    -0.07
    xa
    -0.07
     upset
    -0.07
    POSITIVE LOGITS
    heimer
    0.10
    urs
    0.10
    inel
    0.10
    ater
    0.09
    atomy
    0.09
    heim
    0.09
    INE
    0.09
    paper
    0.09
     amen
    0.09
    OTH
    0.08
    Activations Density 0.001%

    No Known Activations