© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    population figures

    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
     aesthetic
    -0.09
     sensit
    -0.09
     acquaint
    -0.08
    monds
    -0.08
     Original
    -0.08
    -column
    -0.08
     forbidden
    -0.08
    -fe
    -0.08
    ubs
    -0.08
     actual
    -0.08
    POSITIVE LOGITS
    odb
    0.12
    elper
    0.11
     reliable
    0.10
     reliably
    0.10
    rame
    0.10
    uhan
    0.10
     Coff
    0.10
     detected
    0.10
    /releases
    0.10
     pudo
    0.10
    Activations Density 0.002%

    No Known Activations