© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    `lines`, `paragraph`, `text`, `Cell`, `Enum`

    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
     arrang
    -0.09
    .ent
    -0.09
     tantr
    -0.09
    udi
    -0.09
     cerebral
    -0.08
    mitt
    -0.08
    ownload
    -0.08
    audi
    -0.08
    ÑĮ
    -0.08
    rox
    -0.08
    POSITIVE LOGITS
     multip
    0.08
     Ele
    0.08
     plur
    0.08
     solicit
    0.08
    enu
    0.07
     ((((
    0.07
     Long
    0.07
    erman
    0.07
    ks
    0.07
     Ecology
    0.07
    Activations Density 0.267%

    No Known Activations