© 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. 61561
    Prev
    Next
    INDEX
    Explanations

    quilted items

    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
    iero
    -0.11
    aser
    -0.10
    rees
    -0.10
    agne
    -0.10
    oure
    -0.10
    dre
    -0.10
    ieri
    -0.10
    thumbs
    -0.10
     (!((
    -0.09
     bicycle
    -0.09
    POSITIVE LOGITS
    ts
    0.10
    al
    0.09
    ty
    0.09
     Cold
    0.09
     dat
    0.08
    ting
    0.08
    ta
    0.08
    aying
    0.08
     quil
    0.08
    åı°
    0.08
    Activations Density 0.001%

    No Known Activations