© 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. 5582
    Prev
    Next
    INDEX
    Explanations

    Hein/Ein/in followed by names or word parts

    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
    -0.09
    esc
    -0.09
    ario
    -0.09
     unreliable
    -0.09
     Dort
    -0.09
    xes
    -0.08
    utton
    -0.08
    404
    -0.08
    xia
    -0.08
     working
    -0.08
    POSITIVE LOGITS
    onen
    0.12
    eko
    0.11
    orado
    0.11
    ihu
    0.10
    ikki
    0.10
    fragistics
    0.09
     reb
    0.09
     reinc
    0.09
    hardt
    0.09
    ernet
    0.09
    Activations Density 0.045%

    No Known Activations