© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27484
    Prev
    Next
    INDEX
    Explanations

    human and animal comparison

    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
     masc
    -0.13
    Hostname
    -0.11
     Mattis
    -0.11
     bodily
    -0.11
     outdoors
    -0.10
    erra
    -0.10
     neckline
    -0.10
     animals
    -0.10
    animals
    -0.10
     pets
    -0.10
    POSITIVE LOGITS
     human
    0.57
     humans
    0.54
     Humans
    0.44
     Human
    0.41
    human
    0.41
    -human
    0.40
    Humans
    0.39
    Human
    0.39
    _human
    0.37
     humanoid
    0.32
    Activations Density 0.979%

    No Known Activations