© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116386
    Prev
    Next
    INDEX
    Explanations

    asking to borrow or use

    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
    ona
    -0.10
     Lem
    -0.10
     Conte
    -0.09
     aroused
    -0.09
     Turk
    -0.09
     Mayer
    -0.09
     Glover
    -0.09
     endless
    -0.09
     Lond
    -0.09
     arous
    -0.09
    POSITIVE LOGITS
     borrow
    0.16
     Borrow
    0.13
    ASK
    0.12
    borrow
    0.12
     interest
    0.11
     PLEASE
    0.11
     bor
    0.11
    interest
    0.10
     ask
    0.10
     borr
    0.10
    Activations Density 0.047%

    No Known Activations