© 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. 32074
    Prev
    Next
    INDEX
    Explanations

    hidden locations

    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
    horn
    -0.13
     intrusion
    -0.10
    lena
    -0.10
    loe
    -0.09
    isse
    -0.09
    into
    -0.09
    reten
    -0.09
    Into
    -0.09
     lou
    -0.09
     NUM
    -0.09
    POSITIVE LOGITS
     behind
    0.15
     beneath
    0.13
     amongst
    0.13
     underneath
    0.12
     hidden
    0.12
     by
    0.11
     under
    0.10
    (hidden
    0.10
     omin
    0.09
     due
    0.09
    Activations Density 0.006%

    No Known Activations