© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    This followed by definition

    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
     likes
    -0.09
     trusts
    -0.08
     sings
    -0.07
    ceiver
    -0.07
     various
    -0.07
     undert
    -0.07
     ponder
    -0.06
     recruit
    -0.06
     avail
    -0.06
    :
    -0.06
    POSITIVE LOGITS
     means
    0.18
     latter
    0.15
     Means
    0.15
     happened
    0.13
     includes
    0.12
     implies
    0.12
     translates
    0.12
     leads
    0.12
     resulted
    0.12
    means
    0.12
    Activations Density 0.761%

    No Known Activations