© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    -ard endings

    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
    e
    -0.14
    s
    -0.11
    eon
    -0.10
    scape
    -0.09
    mini
    -0.09
    irth
    -0.09
     continuity
    -0.09
    cker
    -0.09
    stitutions
    -0.09
    eeee
    -0.09
    POSITIVE LOGITS
    edly
    0.16
    er
    0.15
    t
    0.13
    robe
    0.13
    inals
    0.13
    ship
    0.13
    erer
    0.13
    ed
    0.13
    quo
    0.13
    inal
    0.12
    Activations Density 0.178%

    No Known Activations