© 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. 55664
    Prev
    Next
    INDEX
    Explanations

    with a little

    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
    brick
    -0.09
    ubo
    -0.08
    è©
    -0.08
     Petite
    -0.08
    pare
    -0.08
    ub
    -0.08
    bens
    -0.08
    erd
    -0.08
     clutch
    -0.07
    wid
    -0.07
    POSITIVE LOGITS
     effort
    0.13
     careful
    0.13
     proper
    0.12
     intervention
    0.11
     continued
    0.11
     practice
    0.11
     repeated
    0.10
     Continued
    0.10
     applied
    0.10
    proper
    0.10
    Activations Density 0.100%

    No Known Activations