© 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. 54444
    Prev
    Next
    INDEX
    Explanations

    official proceedings and news alerts

    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
    lig
    -0.09
    -ap
    -0.08
    cce
    -0.08
     peacefully
    -0.08
    umps
    -0.08
     legally
    -0.08
     confisc
    -0.08
     brow
    -0.07
     errorMsg
    -0.07
    forc
    -0.07
    POSITIVE LOGITS
     Des
    0.10
     chamber
    0.09
    earing
    0.09
    igh
    0.09
     Chamber
    0.09
     Hearing
    0.09
    rod
    0.09
     briefed
    0.08
     pooling
    0.08
    ksam
    0.08
    Activations Density 0.004%

    No Known Activations