© 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. 6606
    Prev
    Next
    INDEX
    Explanations

    quantities or achievements

    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
    cala
    -0.08
    ensi
    -0.08
     Kai
    -0.08
     ultimately
    -0.08
     updateUser
    -0.08
     EXPRESS
    -0.08
     tal
    -0.08
     relentlessly
    -0.08
     falsely
    -0.08
    xi
    -0.08
    POSITIVE LOGITS
     shade
    0.12
     feat
    0.12
     TBD
    0.11
     enclave
    0.10
     sixty
    0.10
     testament
    0.10
     eighty
    0.10
     seventy
    0.10
     affair
    0.10
     blend
    0.09
    Activations Density 0.072%

    No Known Activations