© 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. 2333
    Prev
    Next
    INDEX
    Explanations

    give

    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
     chill
    -0.09
    ptime
    -0.09
     decid
    -0.09
    /alert
    -0.09
    baugh
    -0.09
    outines
    -0.09
    -vars
    -0.09
     Midi
    -0.09
    fol
    -0.08
    Hits
    -0.08
    POSITIVE LOGITS
     pin
    0.10
     exp
    0.09
    pins
    0.08
     pinned
    0.08
    oda
    0.08
    pin
    0.08
     Pin
    0.08
     pepp
    0.07
     lul
    0.07
    jax
    0.07
    Activations Density 0.270%

    No Known Activations