© 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. 3547
    Prev
    Next
    INDEX
    Explanations

    it right

    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
    h
    -0.07
     solid
    -0.07
    iard
    -0.07
    hof
    -0.06
     Bison
    -0.06
     epit
    -0.06
    s
    -0.06
     Mig
    -0.06
    etch
    -0.06
     oct
    -0.06
    POSITIVE LOGITS
     quits
    0.13
     himself
    0.12
     Yourself
    0.11
    adem
    0.11
     escalating
    0.11
     yourself
    0.11
    errupted
    0.10
     Pest
    0.10
     yourselves
    0.10
    ter
    0.10
    Activations Density 0.172%

    No Known Activations