© 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. 90420
    Prev
    Next
    INDEX
    Explanations

    names with titles or suffixes

    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
    /as
    -0.11
     envelope
    -0.09
     bans
    -0.09
    idan
    -0.09
    anium
    -0.09
     ob
    -0.09
     dicts
    -0.09
    isce
    -0.09
     oss
    -0.09
    zia
    -0.09
    POSITIVE LOGITS
     Jr
    0.24
     who
    0.20
    who
    0.18
     Sr
    0.16
     whom
    0.15
     jr
    0.15
     III
    0.13
     fils
    0.12
    —who
    0.12
     Junior
    0.11
    Activations Density 1.014%

    No Known Activations