© 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. 88585
    Prev
    Next
    INDEX
    Explanations

    receiving or giving to someone

    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
    ikel
    -0.09
    ayan
    -0.08
    ooth
    -0.08
     dojo
    -0.08
     interoper
    -0.08
    PX
    -0.08
     interchange
    -0.08
    iro
    -0.08
     SPDX
    -0.08
     Bas
    -0.07
    POSITIVE LOGITS
     headaches
    0.15
     trouble
    0.12
     hugs
    0.12
     bruises
    0.12
     misinformation
    0.11
    idan
    0.11
     lessons
    0.11
     money
    0.11
    spi
    0.11
     headache
    0.11
    Activations Density 0.024%

    No Known Activations