© 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. 32700
    Prev
    Next
    INDEX
    Explanations

    young middle-aged ordinary orphan

    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
     teammate
    -0.12
     nearby
    -0.10
     similarly
    -0.10
     colleague
    -0.10
    omm
    -0.10
     friend
    -0.09
     nearest
    -0.09
     Witt
    -0.09
     proceeded
    -0.09
     colleagues
    -0.09
    POSITIVE LOGITS
     middle
    0.17
     orphan
    0.15
     young
    0.15
     midd
    0.14
     born
    0.13
     eighteen
    0.13
     ordinary
    0.12
     lon
    0.12
     mid
    0.12
     lonely
    0.12
    Activations Density 0.048%

    No Known Activations