© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    state of

    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
    ies
    -0.09
    /state
    -0.08
    ument
    -0.08
    rit
    -0.08
    isle
    -0.08
     Bates
    -0.07
    allback
    -0.07
     reserve
    -0.07
    ault
    -0.07
    iz
    -0.07
    POSITIVE LOGITS
    ful
    0.16
    fulness
    0.15
    FUL
    0.13
    esi
    0.11
     Machines
    0.11
    cheng
    0.10
    amac
    0.10
     Sink
    0.10
    edly
    0.10
     COPYING
    0.10
    Activations Density 0.083%

    No Known Activations