© 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. 50599
    Prev
    Next
    INDEX
    Explanations

    names starting with Nab or Nem

    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
    arella
    -0.11
    heim
    -0.10
     Mirror
    -0.09
     insured
    -0.09
     ride
    -0.09
     mirror
    -0.09
    -rated
    -0.09
     yö
    -0.09
    >[]
    -0.09
     sadly
    -0.09
    POSITIVE LOGITS
     joking
    0.10
     laughter
    0.10
    matter
    0.09
     Brom
    0.09
     laughed
    0.09
    kf
    0.09
    iez
    0.09
     kf
    0.08
    inking
    0.08
     laughing
    0.08
    Activations Density 0.001%

    No Known Activations