© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    numbers followed by closing parenthesis

    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
    loth
    -0.11
    .@
    -0.11
    bish
    -0.11
    lash
    -0.10
     TAR
    -0.10
    ereotype
    -0.10
    "struct
    -0.10
    sss
    -0.09
    hift
    -0.09
    upro
    -0.09
    POSITIVE LOGITS
    ies
    0.09
     manifest
    0.08
    ent
    0.08
    rie
    0.08
     exact
    0.07
    fully
    0.07
     Fog
    0.07
    CHE
    0.07
    ENTS
    0.07
     McCarthy
    0.07
    Activations Density 0.029%

    No Known Activations