© 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. 90835
    Prev
    Next
    INDEX
    Explanations

    Rod names

    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
     Prov
    -0.10
     lastname
    -0.10
    RAIN
    -0.10
    -Assad
    -0.09
    Crypt
    -0.09
     PCS
    -0.09
     nail
    -0.09
     hints
    -0.09
     latex
    -0.09
     tipping
    -0.09
    POSITIVE LOGITS
     Rod
    0.18
     rod
    0.17
    Rod
    0.16
     rods
    0.14
    rod
    0.13
     Rodrig
    0.11
     Rodgers
    0.11
     Rodney
    0.11
     Rodr
    0.11
     Rodriguez
    0.10
    Activations Density 0.046%

    No Known Activations