© 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. 6470
    Prev
    Next
    INDEX
    Explanations

    corners

    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
     heterogeneous
    -0.10
     Suff
    -0.09
    ibel
    -0.09
    amer
    -0.09
     unprecedented
    -0.08
     Rum
    -0.08
    lesh
    -0.08
     scent
    -0.08
    -shell
    -0.08
    cdc
    -0.08
    POSITIVE LOGITS
    èIJ
    0.12
    idon
    0.11
     recept
    0.10
     mouth
    0.10
     Mouth
    0.10
    ertas
    0.10
    earing
    0.10
    ãģĸ
    0.10
     feared
    0.09
     Mahmoud
    0.09
    Activations Density 0.006%

    No Known Activations