© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33200
    Prev
    Next
    INDEX
    Explanations

    legal precedence, boarding school, pregnant women

    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
    usi
    -0.09
    -but
    -0.09
     violated
    -0.09
    bre
    -0.08
     chunks
    -0.08
     chunk
    -0.08
     Bre
    -0.08
     summarized
    -0.08
     dong
    -0.08
     summarizes
    -0.07
    POSITIVE LOGITS
    shall
    0.13
     Shall
    0.13
     shall
    0.12
     predomin
    0.11
     insan
    0.11
     Plaint
    0.11
    bon
    0.10
     predominantly
    0.10
     -*
    0.10
    contro
    0.10
    Activations Density 1.992%

    No Known Activations