© 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. 3648
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by connector

    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
     DAL
    -0.09
    wise
    -0.09
     Dome
    -0.09
    ÛĮد
    -0.08
    UTH
    -0.08
     blo
    -0.08
     thereof
    -0.08
     occupied
    -0.08
    Nib
    -0.08
    aura
    -0.08
    POSITIVE LOGITS
     laps
    0.09
    uye
    0.09
     unl
    0.09
    "in
    0.08
     CROSS
    0.08
    /drivers
    0.08
     Fog
    0.08
     hei
    0.08
    rst
    0.08
    .mov
    0.08
    Activations Density 0.324%

    No Known Activations