© 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. 5353
    Prev
    Next
    INDEX
    Explanations

    girl's, girls', boy's, children

    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
     Tanner
    -0.10
     Concord
    -0.09
    inar
    -0.09
     pam
    -0.08
     Glam
    -0.08
     beware
    -0.08
     empowerment
    -0.08
     Pam
    -0.08
    ird
    -0.07
    cap
    -0.07
    POSITIVE LOGITS
     quotid
    0.11
     Randall
    0.10
     vests
    0.10
    VS
    0.10
     Ranking
    0.10
     Rocks
    0.10
    Ĥæķ°
    0.10
     cerc
    0.10
     Decomp
    0.09
    inyin
    0.09
    Activations Density 0.011%

    No Known Activations