© 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. 114651
    Prev
    Next
    INDEX
    Explanations

    Az followed by 'io', 'lan', 'ale', 'ar'

    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
    es
    -0.11
    (es
    -0.10
    Discovery
    -0.10
    itore
    -0.10
     discharge
    -0.09
     Men
    -0.09
    esp
    -0.09
     thrust
    -0.09
    fault
    -0.09
    ickle
    -0.09
    POSITIVE LOGITS
    rael
    0.10
     impress
    0.10
    izin
    0.10
    azzi
    0.10
    ŀ
    0.09
    nze
    0.09
    обÑĭ
    0.08
    azi
    0.08
    iento
    0.08
    ienza
    0.08
    Activations Density 0.048%

    No Known Activations