© 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. 5716
    Prev
    Next
    INDEX
    Explanations

    slay, play, assay, relay prefixes

    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
    sy
    -0.10
    ijn
    -0.09
    imest
    -0.09
    osti
    -0.09
     AREA
    -0.08
    sel
    -0.08
    pler
    -0.08
    scri
    -0.08
     nowhere
    -0.08
    lest
    -0.07
    POSITIVE LOGITS
    ed
    0.20
    edBy
    0.15
    edb
    0.13
    eed
    0.13
    edback
    0.13
    eurs
    0.13
    ee
    0.13
    e
    0.12
    wers
    0.11
    ega
    0.11
    Activations Density 0.028%

    No Known Activations