© 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. 113329
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     qualifications
    -0.08
    roph
    -0.07
    urn
    -0.07
     Trou
    -0.07
     eligibility
    -0.07
     contra
    -0.07
    ("**
    -0.07
     balance
    -0.07
     examples
    -0.07
    ime
    -0.07
    POSITIVE LOGITS
     it
    0.14
    adem
    0.12
    -it
    0.12
     standout
    0.12
    ubo
    0.10
    unas
    0.10
     deliveries
    0.10
    BEST
    0.10
     placements
    0.10
     It
    0.10
    Activations Density 0.050%

    No Known Activations