© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    again or similar

    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
     Hawk
    -0.09
    /stdc
    -0.09
    оÑı
    -0.09
    aws
    -0.09
    rove
    -0.08
     deb
    -0.08
    sburg
    -0.08
    stdexcept
    -0.08
    -Methods
    -0.08
     honestly
    -0.08
    POSITIVE LOGITS
     again
    0.12
     novamente
    0.11
    again
    0.09
    _again
    0.09
    åĨį
    0.08
     same
    0.08
    IES
    0.08
     Again
    0.08
    ardy
    0.08
    star
    0.08
    Activations Density 0.969%

    No Known Activations