© 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. 32719
    Prev
    Next
    INDEX
    Explanations

    pronoun "we" followed by a verb

    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
     myself
    -0.13
    iani
    -0.13
    mit
    -0.10
    hari
    -0.10
    hti
    -0.09
     meine
    -0.09
    715
    -0.09
     suppose
    -0.09
     owned
    -0.09
    ÑĢа
    -0.09
    POSITIVE LOGITS
    Ñģли
    0.11
     need
    0.11
     Wel
    0.11
     apprec
    0.10
    ird
    0.10
     NEED
    0.10
    zel
    0.10
     welcome
    0.10
    heard
    0.09
    elcome
    0.09
    Activations Density 0.049%

    No Known Activations