© 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. 13873
    Prev
    Next
    INDEX
    Explanations

    animal actions and states

    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
    Negative Logits
     animals
    -0.16
     Animals
    -0.13
    adel
    -0.11
     animal
    -0.11
    animals
    -0.11
    Animal
    -0.10
    semb
    -0.10
     pets
    -0.10
     horses
    -0.10
     creatures
    -0.10
    POSITIVE LOGITS
     mate
    0.13
    uin
    0.10
     McM
    0.10
    /is
    0.10
     unfavor
    0.10
    ETA
    0.09
    asca
    0.09
    endi
    0.09
     proverb
    0.09
     pray
    0.09
    Activations Density 0.090%

    No Known Activations