© 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. 27716
    Prev
    Next
    INDEX
    Explanations

    obtaining or acquiring information

    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
     dara
    -0.10
    iani
    -0.10
    els
    -0.09
    icode
    -0.09
    ullen
    -0.09
    awan
    -0.08
    omedical
    -0.08
    obi
    -0.08
    iza
    -0.08
    anel
    -0.08
    POSITIVE LOGITS
     accessing
    0.14
     acquiring
    0.13
    à¸ģาร
    0.12
     securing
    0.12
     regarding
    0.12
     retrieving
    0.11
     obtaining
    0.11
    getting
    0.11
    ãĥ¼ãĤ¹
    0.11
     constructing
    0.10
    Activations Density 1.591%

    No Known Activations