© 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. 54973
    Prev
    Next
    INDEX
    Explanations

    details: ISBN

    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
    gom
    -0.09
     Pap
    -0.09
     ved
    -0.09
    wid
    -0.08
     propriet
    -0.08
    EK
    -0.08
    edly
    -0.08
    sp
    -0.08
     Mic
    -0.08
    oyer
    -0.08
    POSITIVE LOGITS
    fts
    0.09
    BITS
    0.09
    esh
    0.09
    \u
    0.08
     Amar
    0.08
     DISP
    0.08
    ammo
    0.08
     letters
    0.08
    CORE
    0.08
    ane
    0.08
    Activations Density 0.001%

    No Known Activations