© 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. 57414
    Prev
    Next
    INDEX
    Explanations

    bruises, rash, wet, soggy

    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
     Salv
    -0.09
    lic
    -0.09
     createStore
    -0.08
     sinks
    -0.08
     damaged
    -0.08
    leaf
    -0.08
     prest
    -0.08
     leaf
    -0.08
     Leh
    -0.08
    lijah
    -0.08
    POSITIVE LOGITS
     rad
    0.09
     Gam
    0.09
     HAL
    0.08
     bre
    0.08
    ika
    0.08
    .Compute
    0.08
    gran
    0.08
    ÑĢаз
    0.08
     nog
    0.08
    rud
    0.08
    Activations Density 0.021%

    No Known Activations