© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46340
    Prev
    Next
    INDEX
    Explanations

    numbers 15-20

    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
     vale
    -0.09
     Friday
    -0.09
    135
    -0.09
     friday
    -0.08
    avage
    -0.08
     vac
    -0.08
     Fri
    -0.07
    615
    -0.07
     Scripts
    -0.07
     TIFF
    -0.07
    POSITIVE LOGITS
    17
    0.26
     seventeen
    0.24
    16
    0.22
    18
    0.21
     sixteen
    0.20
     eighteen
    0.20
    19
    0.19
     XVI
    0.17
     nineteen
    0.17
    20
    0.15
    Activations Density 0.218%

    No Known Activations