© 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. 3239
    Prev
    Next
    INDEX
    Explanations

    additional, second, again

    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
    idi
    -0.09
     originals
    -0.09
     aph
    -0.08
     cdr
    -0.08
    erb
    -0.08
    au
    -0.08
    ITE
    -0.08
    ivo
    -0.08
     Pet
    -0.08
    azing
    -0.08
    POSITIVE LOGITS
     additional
    0.24
     Additional
    0.21
    Additional
    0.19
    additional
    0.19
     again
    0.18
     second
    0.17
    _additional
    0.17
    .additional
    0.17
    Again
    0.16
     Again
    0.16
    Activations Density 0.448%

    No Known Activations