© 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. 57704
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences

    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
     Urs
    -0.09
    odo
    -0.08
    wik
    -0.08
    hec
    -0.07
    lane
    -0.07
     sing
    -0.07
    _cre
    -0.07
     Means
    -0.07
     Mour
    -0.07
    balls
    -0.07
    POSITIVE LOGITS
    ette
    0.10
    ington
    0.09
     doubt
    0.09
    esis
    0.09
    emic
    0.08
    tlement
    0.08
    ennon
    0.08
    akte
    0.08
     Permission
    0.08
     punt
    0.08
    Activations Density 0.001%

    No Known Activations