© 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. 14984
    Prev
    Next
    INDEX
    Explanations

    email addresses and 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
     Her
    -0.10
    azen
    -0.09
     aun
    -0.09
     Darren
    -0.08
     Sund
    -0.08
     rocked
    -0.08
    acute
    -0.08
    Her
    -0.07
     Mercer
    -0.07
     Major
    -0.07
    POSITIVE LOGITS
     Mrs
    0.35
     Sir
    0.32
     Mad
    0.30
     Miss
    0.29
    Mrs
    0.28
     Mr
    0.26
    Sir
    0.25
    Miss
    0.24
    Mad
    0.23
    Mr
    0.21
    Activations Density 0.149%

    No Known Activations