© 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. 26125
    Prev
    Next
    INDEX
    Explanations

    adverbs and then verbs/nouns

    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
     Respect
    -0.11
    ||(
    -0.11
    ollo
    -0.10
    Forever
    -0.10
    quier
    -0.10
    iev
    -0.10
     respect
    -0.10
    yas
    -0.10
     NTN
    -0.10
     plated
    -0.10
    POSITIVE LOGITS
     simultaneously
    0.15
     rapidly
    0.14
     sharply
    0.14
     simultaneous
    0.13
     simult
    0.12
     abruptly
    0.12
     suddenly
    0.12
     fart
    0.11
     progressively
    0.11
     sudden
    0.11
    Activations Density 0.172%

    No Known Activations