© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91483
    Prev
    Next
    INDEX
    Explanations

    time units and quantities

    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
    arnation
    -0.09
    antically
    -0.09
    arna
    -0.08
    /goto
    -0.08
     Pers
    -0.08
     Madd
    -0.08
     hum
    -0.08
    MB
    -0.08
     Wal
    -0.08
    Wal
    -0.08
    POSITIVE LOGITS
    -and
    0.25
    ½
    0.17
    -plus
    0.16
    âħ
    0.15
    ¾
    0.15
    ¼
    0.15
     eighty
    0.14
    _and
    0.13
     fifty
    0.12
    -&
    0.12
    Activations Density 0.307%

    No Known Activations