© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    study and research contexts

    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
    VERY
    -0.10
     sortable
    -0.10
    variably
    -0.09
     VERY
    -0.09
    erd
    -0.09
     hors
    -0.09
     Pang
    -0.09
    Jason
    -0.09
    ILD
    -0.09
     triang
    -0.09
    POSITIVE LOGITS
     anyway
    0.19
     anyhow
    0.16
     anyways
    0.15
    Anyway
    0.10
    ogen
    0.10
    ols
    0.09
     vict
    0.09
     abl
    0.09
     precedent
    0.08
    æľ¬
    0.08
    Activations Density 0.067%

    No Known Activations