© 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. 3437
    Prev
    Next
    INDEX
    Explanations

    entity & number

    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
    ence
    -0.11
    ishes
    -0.10
    ص
    -0.10
    wan
    -0.09
     Mann
    -0.09
    ences
    -0.09
    Ed
    -0.09
     arrang
    -0.09
    еж
    -0.08
    udes
    -0.08
    POSITIVE LOGITS
    CDATA
    0.14
    nosis
    0.10
    ervisor
    0.10
    OTH
    0.08
    avern
    0.08
    inyin
    0.08
    ovel
    0.08
     tamp
    0.08
    thesis
    0.08
    auss
    0.08
    Activations Density 0.098%

    No Known Activations