© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    reciprocal and mutual exchanges

    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
    kop
    -0.10
     collectively
    -0.09
     Seam
    -0.09
    gee
    -0.09
     centrally
    -0.09
    ERP
    -0.09
    pri
    -0.09
    priv
    -0.08
    etter
    -0.08
    ux
    -0.08
    POSITIVE LOGITS
     respect
    0.13
     respectful
    0.11
     trust
    0.11
     Relations
    0.11
     beneficial
    0.10
    ymb
    0.10
     between
    0.10
     symb
    0.10
     tussen
    0.10
     relationship
    0.10
    Activations Density 0.043%

    No Known Activations