© 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. 88408
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Gilbert
    -0.10
    LLL
    -0.10
    NM
    -0.09
    ëĭ¹
    -0.09
     Schul
    -0.09
     Kits
    -0.09
    ampa
    -0.09
     busy
    -0.09
    _sv
    -0.09
     pel
    -0.09
    POSITIVE LOGITS
     respectfully
    0.10
    bose
    0.10
     etiquette
    0.09
    lest
    0.09
     personalized
    0.09
    aka
    0.08
    aves
    0.08
     respect
    0.08
     Respect
    0.08
     polit
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.