© 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. 116608
    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
    endo
    -0.10
    oin
    -0.10
    iesen
    -0.09
    inson
    -0.09
     pelos
    -0.09
    ASC
    -0.09
    kus
    -0.09
    hes
    -0.09
    react
    -0.09
    oit
    -0.09
    POSITIVE LOGITS
    dess
    0.10
    /prom
    0.10
     decision
    0.10
    inal
    0.09
    /profile
    0.09
    ()?.
    0.09
    -this
    0.09
     that
    0.09
     bahwa
    0.09
     sund
    0.09
    Activations Density 0.000%

    No Known Activations