© 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. 54894
    Prev
    Next
    INDEX
    Explanations

    quotes or code comments

    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
     Westbrook
    -0.09
    edin
    -0.09
     """č↵č↵
    -0.09
     arrang
    -0.09
    iana
    -0.08
    ĮĢ
    -0.08
    }],↵
    -0.08
     ret
    -0.08
     Harper
    -0.08
     Sü
    -0.08
    POSITIVE LOGITS
     typeof
    0.08
     mari
    0.08
     Wis
    0.07
     couch
    0.07
     partnerships
    0.07
    uce
    0.07
     consequently
    0.07
    ymes
    0.07
    lico
    0.07
     failing
    0.07
    Activations Density 0.096%

    No Known Activations