© 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. 7253
    Prev
    Next
    INDEX
    Explanations

    written by quotes

    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
    .tech
    -0.10
     Lum
    -0.09
     kinetic
    -0.09
    GRE
    -0.08
    arov
    -0.08
     lum
    -0.08
     Mandal
    -0.08
     Neo
    -0.08
     brilliance
    -0.08
    Illuminate
    -0.07
    POSITIVE LOGITS
     Walt
    0.11
     Cly
    0.11
     affinity
    0.10
     hairy
    0.10
     Soul
    0.10
     Relax
    0.10
     incur
    0.10
    zag
    0.10
     Budd
    0.10
     budd
    0.10
    Activations Density 0.120%

    No Known Activations