© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111670
    Prev
    Next
    INDEX
    Explanations

    said or told

    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
     incred
    -0.10
    TG
    -0.09
     promise
    -0.08
    omo
    -0.08
     Miles
    -0.08
    itat
    -0.08
     neces
    -0.08
    756
    -0.07
     compos
    -0.07
     poss
    -0.07
    POSITIVE LOGITS
     told
    0.18
     mentioned
    0.15
     mention
    0.15
     Mention
    0.14
     mentioning
    0.13
     relay
    0.13
     tell
    0.13
     tells
    0.13
     mentions
    0.12
     informed
    0.12
    Activations Density 0.123%

    No Known Activations