© 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. 50068
    Prev
    Next
    INDEX
    Explanations

    let followed by pronoun or 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
     Fine
    -0.10
    asm
    -0.10
     Mae
    -0.09
     Verb
    -0.09
     Grim
    -0.09
     Quit
    -0.08
    rib
    -0.08
    Fine
    -0.08
    recogn
    -0.08
    ammer
    -0.08
    POSITIVE LOGITS
    urd
    0.09
     resonance
    0.09
    union
    0.09
     rever
    0.09
    659
    0.09
    alle
    0.09
    /com
    0.08
     uttered
    0.08
     RL
    0.08
    215
    0.08
    Activations Density 0.019%

    No Known Activations