© 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. 91757
    Prev
    Next
    INDEX
    Explanations

    names of people and sources

    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
     pec
    -0.10
    weigh
    -0.10
    isch
    -0.10
    olly
    -0.09
    itur
    -0.09
     gris
    -0.09
     Bog
    -0.09
     bog
    -0.09
    arin
    -0.09
    dec
    -0.09
    POSITIVE LOGITS
     Alto
    0.10
    @a
    0.08
     Ny
    0.08
     yourselves
    0.08
     alternative
    0.08
     Mig
    0.08
     Western
    0.08
     federally
    0.07
     Ain
    0.07
     predictor
    0.07
    Activations Density 0.001%

    No Known Activations