© 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. 89295
    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
    sim
    -0.10
    YRO
    -0.10
     Suites
    -0.10
     Gio
    -0.10
     Harm
    -0.10
     fluffy
    -0.10
    Ef
    -0.09
     trouble
    -0.09
    ads
    -0.09
    ymes
    -0.09
    POSITIVE LOGITS
    ape
    0.09
    arkin
    0.09
     signific
    0.08
     surrendered
    0.08
     Tiger
    0.08
     fundament
    0.08
    rone
    0.07
    ihu
    0.07
     Heg
    0.07
    unda
    0.07
    Activations Density 0.000%

    No Known Activations