© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    prefix + -ia, -ara, -era, -uli

    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
    leigh
    -0.08
    ledge
    -0.08
     cuts
    -0.07
     REC
    -0.07
    elow
    -0.07
     duly
    -0.07
    leri
    -0.07
    tel
    -0.07
    illac
    -0.07
    ickle
    -0.07
    POSITIVE LOGITS
     Longer
    0.11
     Moor
    0.10
    dehyde
    0.10
    arith
    0.09
     longer
    0.09
    .dp
    0.09
    .policy
    0.09
    ed
    0.09
    efa
    0.09
    :name
    0.09
    Activations Density 0.283%

    No Known Activations