© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55166
    Prev
    Next
    INDEX
    Explanations

    `CharField` `maxlength` `upload_to`

    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
     theirs
    -0.09
    sei
    -0.09
    azen
    -0.08
    vak
    -0.08
    /story
    -0.08
    umm
    -0.08
     samo
    -0.08
    Dock
    -0.08
     Dek
    -0.08
    ounded
    -0.07
    POSITIVE LOGITS
    iest
    0.11
    eds
    0.09
     counts
    0.09
    ник
    0.09
     Wes
    0.08
     sig
    0.08
    sites
    0.08
    HIP
    0.08
     зап
    0.08
     governors
    0.08
    Activations Density 0.002%

    No Known Activations