© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2310
    Prev
    Next
    INDEX
    Explanations

    positive descriptors for quality

    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
    ikh
    -0.09
     Revel
    -0.09
    sth
    -0.09
    imits
    -0.08
    yal
    -0.08
    loff
    -0.08
    hung
    -0.08
     Parenthood
    -0.08
    hp
    -0.08
    .tv
    -0.08
    POSITIVE LOGITS
     price
    0.10
     decent
    0.09
     reasonably
    0.09
     convenient
    0.09
     Price
    0.08
     amenities
    0.08
    pler
    0.08
     zad
    0.08
     cont
    0.08
     retro
    0.08
    Activations Density 0.375%

    No Known Activations