© 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. 56191
    Prev
    Next
    INDEX
    Explanations

    directory path separator

    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
    orig
    -0.10
    olls
    -0.09
    ól
    -0.09
    ead
    -0.09
    ento
    -0.09
    hai
    -0.09
    adro
    -0.09
    iot
    -0.08
    yes
    -0.08
    contre
    -0.08
    POSITIVE LOGITS
    ate
    0.09
    ates
    0.09
    amento
    0.09
    .apps
    0.09
    Ñģк
    0.08
    atem
    0.08
     topping
    0.08
    inded
    0.08
    ond
    0.08
    251
    0.08
    Activations Density 0.005%

    No Known Activations