© 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. 54587
    Prev
    Next
    INDEX
    Explanations

    "type": value definition

    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
    ensi
    -0.09
    omic
    -0.08
    tes
    -0.08
    ground
    -0.08
    oret
    -0.08
     NIL
    -0.08
    ity
    -0.07
    amba
    -0.07
    eg
    -0.07
    iling
    -0.07
    POSITIVE LOGITS
    hoot
    0.10
     Patch
    0.09
    star
    0.09
    leck
    0.09
    heimer
    0.09
    .(*
    0.09
     natur
    0.09
    ť
    0.09
    Nat
    0.09
     BRAND
    0.09
    Activations Density 0.019%

    No Known Activations