© 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. 111432
    Prev
    Next
    INDEX
    Explanations

    Robert

    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
    Negative Logits
    [R
    -0.15
     r
    -0.12
    RR
    -0.11
    [r
    -0.10
     RD
    -0.10
     RID
    -0.10
     CRA
    -0.10
     Rc
    -0.10
    rir
    -0.10
     RU
    -0.10
    POSITIVE LOGITS
    åı°
    0.10
     Tort
    0.08
     Bob
    0.08
    -fed
    0.08
     cherry
    0.08
     Measure
    0.08
    BUY
    0.08
    dling
    0.08
     Presenter
    0.08
    nesia
    0.08
    Activations Density 0.175%

    No Known Activations