© 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. 33906
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     Barb
    -0.09
    adro
    -0.09
    unte
    -0.09
     proprio
    -0.09
     Schro
    -0.09
    pii
    -0.09
     entsprech
    -0.09
     damn
    -0.09
    ORMAL
    -0.09
    ugen
    -0.08
    POSITIVE LOGITS
     Extr
    0.11
     overall
    0.10
     cult
    0.10
     Je
    0.09
     checker
    0.09
    enia
    0.09
    -ci
    0.09
     anchors
    0.09
    Overall
    0.09
    gb
    0.09
    Activations Density 0.003%

    No Known Activations