© 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. 3783
    Prev
    Next
    INDEX
    Explanations

    suited, fit, and ideal for

    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
    tu
    -0.10
    lut
    -0.10
    bk
    -0.10
    imson
    -0.10
     lest
    -0.09
    ods
    -0.09
     regularly
    -0.09
     Laz
    -0.09
    itta
    -0.08
    ifr
    -0.08
    POSITIVE LOGITS
     suited
    0.16
     suitability
    0.13
     natur
    0.12
     lends
    0.11
     thrive
    0.10
     fit
    0.10
    -su
    0.10
     nature
    0.10
    ering
    0.09
    fit
    0.09
    Activations Density 0.223%

    No Known Activations