© 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. 47031
    Prev
    Next
    INDEX
    Explanations

    whole or entire

    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
     all
    -0.07
     discontin
    -0.06
     total
    -0.06
     fully
    -0.06
     TOTAL
    -0.06
    andes
    -0.06
    vang
    -0.06
    fad
    -0.05
    az
    -0.05
    ilt
    -0.05
    POSITIVE LOGITS
     ordeal
    0.17
    heart
    0.16
     gam
    0.16
    ties
    0.15
     range
    0.14
     spectrum
    0.14
     eternity
    0.14
     populace
    0.14
     array
    0.14
     thing
    0.13
    Activations Density 0.071%

    No Known Activations