© 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. 61642
    Prev
    Next
    INDEX
    Explanations

    but what about

    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
     otherwise
    -0.09
    amt
    -0.08
    otherwise
    -0.08
    onica
    -0.08
     heaps
    -0.08
    ixin
    -0.08
     OTHERWISE
    -0.08
     anyway
    -0.08
    uner
    -0.07
     Troll
    -0.07
    POSITIVE LOGITS
     initiative
    0.10
     rolling
    0.09
    Emer
    0.09
    GP
    0.09
    Extension
    0.08
     seit
    0.08
     Shirley
    0.08
     oversh
    0.08
    pip
    0.08
     nehmen
    0.08
    Activations Density 0.135%

    No Known Activations