© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    identifying or finding names and information

    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
     sequel
    -0.10
     Petra
    -0.10
     Horton
    -0.08
    olta
    -0.08
    ahl
    -0.08
     Stein
    -0.08
     elective
    -0.08
     Exceptions
    -0.08
    gens
    -0.08
    extent
    -0.08
    POSITIVE LOGITS
     interpretation
    0.24
     interpret
    0.21
     identification
    0.21
     Interpret
    0.21
     interpretations
    0.20
     interpreting
    0.20
     WHAT
    0.20
    interpret
    0.20
     Identification
    0.19
     identity
    0.19
    Activations Density 0.508%

    No Known Activations