© 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. 89336
    Prev
    Next
    INDEX
    Explanations

    father or dad figures

    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
    ives
    -0.08
     cripp
    -0.08
     intermediate
    -0.08
    ÌĢ
    -0.08
    éĹ´
    -0.08
    xin
    -0.08
    endant
    -0.08
     McConnell
    -0.08
    platz
    -0.08
    iard
    -0.08
    POSITIVE LOGITS
    uchos
    0.11
    uhe
    0.11
     Futures
    0.10
    dest
    0.10
     ranch
    0.10
    (dy
    0.10
    n
    0.10
    sWith
    0.10
    uil
    0.10
    zano
    0.09
    Activations Density 0.014%

    No Known Activations