© 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. 16492
    Prev
    Next
    INDEX
    Explanations

    property theft and retrieval

    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
     rejects
    -0.11
     dismissing
    -0.10
    iali
    -0.10
     Rut
    -0.10
     Hiring
    -0.10
    ehler
    -0.10
     ignored
    -0.10
     Reject
    -0.10
     recruit
    -0.10
     wäh
    -0.10
    POSITIVE LOGITS
     theft
    0.31
     retrieval
    0.29
     retrieving
    0.27
     reclaim
    0.26
     Retrie
    0.26
     stolen
    0.25
     stealing
    0.25
     retrieve
    0.25
     retrie
    0.25
     stole
    0.24
    Activations Density 0.233%

    No Known Activations