© 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. 18382
    Prev
    Next
    INDEX
    Explanations

    ds/DS/dp/DP abbreviations

    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
    deo
    -0.10
    onen
    -0.08
    poll
    -0.08
    gue
    -0.08
    ebb
    -0.08
    AIM
    -0.07
    омÑĥ
    -0.07
    chten
    -0.07
     EL
    -0.07
    eam
    -0.07
    POSITIVE LOGITS
     slam
    0.11
     Direct
    0.10
     innoc
    0.10
     sandwich
    0.10
     innocent
    0.10
     Heller
    0.10
    asic
    0.10
     slapped
    0.10
     spots
    0.09
     jointly
    0.09
    Activations Density 0.110%

    No Known Activations