© 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. 30818
    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
     Kra
    -0.07
     NG
    -0.07
     fertile
    -0.07
     aud
    -0.07
    aco
    -0.06
     âĢİ
    -0.06
     scrap
    -0.06
    dev
    -0.06
    hind
    -0.06
     comer
    -0.06
    POSITIVE LOGITS
     Burst
    0.12
    stoff
    0.12
     Baz
    0.12
    !";č↵
    0.12
    QR
    0.12
     distracting
    0.12
    uraa
    0.11
     Burl
    0.11
    qv
    0.11
    RTC
    0.11
    Activations Density 0.000%

    No Known Activations