© 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. 56033
    Prev
    Next
    INDEX
    Explanations

    accelerate, escalate

    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
     Wants
    -0.10
    cores
    -0.10
    comments
    -0.10
    arent
    -0.09
    leh
    -0.09
    oked
    -0.09
    atak
    -0.09
    .fm
    -0.09
     Kill
    -0.09
    plements
    -0.09
    POSITIVE LOGITS
     Bark
    0.08
     Lag
    0.08
     Esc
    0.08
     escalate
    0.08
     shock
    0.08
     escalated
    0.07
    vas
    0.07
     tol
    0.07
    eker
    0.07
     unbelievable
    0.07
    Activations Density 0.038%

    No Known Activations