© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    program files and paths

    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
    erp
    -0.09
    <td
    -0.08
     Ronnie
    -0.07
    htar
    -0.07
    ips
    -0.07
     torch
    -0.07
     Tart
    -0.07
    yll
    -0.07
    orr
    -0.07
     bank
    -0.07
    POSITIVE LOGITS
    oler
    0.10
    /Core
    0.10
    	Copyright
    0.10
    ardi
    0.09
     esac
    0.09
    ож
    0.09
    roman
    0.09
     Pai
    0.09
    ober
    0.09
    fv
    0.09
    Activations Density 0.185%

    No Known Activations