© 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. 49896
    Prev
    Next
    INDEX
    Explanations

    bearer or recipient

    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
    fern
    -0.10
     kw
    -0.10
    ften
    -0.10
    -r
    -0.09
     everyone
    -0.09
    lez
    -0.09
     shepherd
    -0.09
     folks
    -0.09
    roz
    -0.09
     everybody
    -0.08
    POSITIVE LOGITS
     bearer
    0.14
     sender
    0.14
     speaker
    0.13
     requester
    0.13
     receiver
    0.13
     recipient
    0.13
     participating
    0.12
     observer
    0.12
     involved
    0.12
     holder
    0.12
    Activations Density 0.691%

    No Known Activations