© 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. 5030
    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
    amil
    -0.12
    /is
    -0.12
     Forge
    -0.11
    quo
    -0.11
     Ships
    -0.11
    QUI
    -0.11
     Raq
    -0.10
     bureaucr
    -0.10
    #af
    -0.10
     trunc
    -0.10
    POSITIVE LOGITS
     McKin
    0.09
     bar
    0.09
     Primitive
    0.08
     bip
    0.08
    pty
    0.08
     env
    0.08
     significantly
    0.08
     Barcelona
    0.08
     dev
    0.07
     barbar
    0.07
    Activations Density 0.000%

    No Known Activations