© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    change, modulation, altered states

    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
    /big
    -0.08
     seize
    -0.07
    bes
    -0.07
    utan
    -0.07
     Step
    -0.07
    atts
    -0.07
     step
    -0.07
    Votes
    -0.07
     Dom
    -0.07
    agnetic
    -0.07
    POSITIVE LOGITS
     balance
    0.15
     depending
    0.13
     Balance
    0.12
     patterns
    0.12
     pattern
    0.12
     negatively
    0.12
     opposite
    0.11
    balance
    0.11
     positively
    0.11
     oppos
    0.11
    Activations Density 0.647%

    No Known Activations