© 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. 33747
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by punctuation

    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
     forth
    -0.11
    haus
    -0.11
     farewell
    -0.11
     Ness
    -0.11
     aloud
    -0.11
     away
    -0.11
     forward
    -0.11
     Hutchinson
    -0.10
    ADS
    -0.10
     Rub
    -0.10
    POSITIVE LOGITS
    ander
    0.10
    /us
    0.10
    /on
    0.09
    itere
    0.08
    dle
    0.08
    w
    0.08
    onne
    0.08
    Temporal
    0.07
     synerg
    0.07
    bir
    0.07
    Activations Density 0.131%

    No Known Activations