© 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. 3971
    Prev
    Next
    INDEX
    Explanations

    What questions

    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
     yourselves
    -0.10
     onboard
    -0.10
    veis
    -0.10
     patched
    -0.09
     Bellev
    -0.09
     lined
    -0.09
     ste
    -0.09
     roaming
    -0.08
    \\"
    -0.08
    broadcast
    -0.08
    POSITIVE LOGITS
     Lud
    0.11
     height
    0.10
     Height
    0.10
     hairstyle
    0.10
     Walton
    0.10
     nationality
    0.10
     Bliss
    0.10
     heights
    0.10
    urm
    0.10
     Chall
    0.10
    Activations Density 0.021%

    No Known Activations