© 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. 55277
    Prev
    Next
    INDEX
    Explanations

    businesses or authors

    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
    ĤŃ
    -0.08
    µ¬
    -0.08
    .or
    -0.08
    Ñĥн
    -0.08
     incoming
    -0.08
    etti
    -0.08
    ¡°
    -0.08
    иÑģк
    -0.08
    Meet
    -0.07
     att
    -0.07
    POSITIVE LOGITS
     Kal
    0.08
     punct
    0.08
    orny
    0.08
    onas
    0.08
     spikes
    0.08
    coli
    0.07
     tongues
    0.07
     bas
    0.07
     adv
    0.07
    otten
    0.07
    Activations Density 0.027%

    No Known Activations