© 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. 54487
    Prev
    Next
    INDEX
    Explanations

    citations, references, abbreviations

    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
    iez
    -0.10
    eton
    -0.10
    REW
    -0.10
    iest
    -0.10
    åij½
    -0.09
     Sac
    -0.09
    })",
    -0.09
    iant
    -0.09
    prot
    -0.09
     vice
    -0.09
    POSITIVE LOGITS
    eken
    0.09
     Manus
    0.07
     sof
    0.07
     cuckold
    0.07
    esi
    0.07
     sober
    0.07
     padre
    0.07
    zas
    0.06
     LLP
    0.06
     drunken
    0.06
    Activations Density 0.006%

    No Known Activations