© 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. 18355
    Prev
    Next
    INDEX
    Explanations

    Med substring

    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
    ogl
    -0.12
     quot
    -0.10
    ives
    -0.09
    ymes
    -0.09
     substit
    -0.09
    steen
    -0.09
    izon
    -0.09
    unfold
    -0.09
    ENSIONS
    -0.09
    icken
    -0.09
    POSITIVE LOGITS
    dle
    0.13
     med
    0.12
    ea
    0.11
     Med
    0.11
     Medina
    0.11
    itations
    0.10
    tech
    0.10
     Median
    0.10
    dy
    0.10
    itative
    0.10
    Activations Density 0.019%

    No Known Activations