© 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. 48769
    Prev
    Next
    INDEX
    Explanations

    Eagle

    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
    ilia
    -0.10
     Hollow
    -0.09
     sensible
    -0.09
    _validate
    -0.09
    ollo
    -0.09
     Pant
    -0.09
    idden
    -0.09
    ily
    -0.09
    dat
    -0.09
    rika
    -0.09
    POSITIVE LOGITS
     eagle
    0.18
    hawk
    0.15
     Eagle
    0.15
    -eyed
    0.12
     soaring
    0.12
     swo
    0.11
    cliffe
    0.11
     Eagles
    0.10
     eag
    0.10
    crest
    0.10
    Activations Density 0.015%

    No Known Activations