© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26812
    Prev
    Next
    INDEX
    Explanations

    wave hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spiritually
    -0.09
    landers
    -0.08
    oru
    -0.08
     Duc
    -0.08
     Aster
    -0.08
     gears
    -0.08
    ilda
    -0.08
     åº
    -0.08
     babes
    -0.08
    ạo
    -0.08
    POSITIVE LOGITS
     goodbye
    0.13
     semaphore
    0.12
     wave
    0.11
     bye
    0.11
     Wave
    0.11
    Wave
    0.10
     corpus
    0.10
    оÑģÑĤи
    0.10
    ÙĪد
    0.10
     hearty
    0.10
    Activations Density 0.043%

    No Known Activations