© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    foundation, machine, parts, obesity, converter

    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
     latina
    -0.10
    —are
    -0.09
     ’
    -0.08
    ared
    -0.08
    ov
    -0.08
    <|fim_suffix|>
    -0.08
    ba
    -0.08
    lv
    -0.07
    ased
    -0.07
    144
    -0.07
    POSITIVE LOGITS
     is
    0.13
     can
    0.13
     was
    0.12
     has
    0.12
     may
    0.12
     will
    0.11
     isn
    0.11
     cannot
    0.11
     must
    0.11
     could
    0.10
    Activations Density 0.948%

    No Known Activations