© 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. 55334
    Prev
    Next
    INDEX
    Explanations

    hexadecimal hashes or identifiers

    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
     orderBy
    -0.09
    nth
    -0.09
     arbitrary
    -0.09
    stub
    -0.09
    yen
    -0.09
     Nom
    -0.09
    æľį
    -0.09
    clusions
    -0.08
     poss
    -0.08
    iner
    -0.08
    POSITIVE LOGITS
     indeed
    0.08
    acon
    0.08
    ertest
    0.08
     lids
    0.07
    pong
    0.07
     (!((
    0.07
     letto
    0.07
    âm
    0.07
    ober
    0.07
     disin
    0.07
    Activations Density 0.012%

    No Known Activations