© 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. 14535
    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
    pone
    -0.11
    rage
    -0.10
    ame
    -0.10
     misunder
    -0.10
    no
    -0.10
    spd
    -0.10
    alus
    -0.09
     fla
    -0.09
    aky
    -0.09
     Fla
    -0.09
    POSITIVE LOGITS
    eing
    0.13
    thic
    0.11
    lek
    0.11
    ingly
    0.11
     rebound
    0.10
    ptive
    0.09
     lum
    0.09
    اء
    0.09
    thr
    0.09
    oner
    0.09
    Activations Density 0.000%

    No Known Activations