© 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. 90652
    Prev
    Next
    INDEX
    Explanations

    up against, up in, up to

    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
    -drop
    -0.10
     enrich
    -0.10
     prof
    -0.09
    Prof
    -0.09
     crossing
    -0.09
     Prof
    -0.09
    ling
    -0.09
    vil
    -0.09
     Crossing
    -0.09
     ext
    -0.08
    POSITIVE LOGITS
     Junk
    0.12
     against
    0.11
    egal
    0.11
     vag
    0.10
    jie
    0.10
    WAYS
    0.09
    ommen
    0.09
    etween
    0.09
    åķĨ
    0.09
     Stein
    0.09
    Activations Density 0.017%

    No Known Activations