© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89547
    Prev
    Next
    INDEX
    Explanations

    distributed with

    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
     gag
    -0.08
     Heap
    -0.08
     Carr
    -0.07
    ouv
    -0.07
     Carrier
    -0.07
     flesh
    -0.07
     taste
    -0.06
     victory
    -0.06
     cross
    -0.06
     rainy
    -0.06
    POSITIVE LOGITS
    dcc
    0.11
     Fro
    0.11
     spar
    0.11
    bfd
    0.11
    burgh
    0.11
     laughs
    0.11
    PWD
    0.10
    kap
    0.10
    ADVERTISEMENT
    0.10
    aston
    0.10
    Activations Density 0.002%

    No Known Activations