© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113232
    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
     jorn
    -0.08
    .ly
    -0.08
    vell
    -0.07
     Billion
    -0.07
     staggering
    -0.07
     è§
    -0.07
     Fathers
    -0.07
     wondered
    -0.07
     ill
    -0.07
     lub
    -0.07
    POSITIVE LOGITS
     replacements
    0.14
     replacement
    0.12
     alternatives
    0.12
    æĽ
    0.12
    heimer
    0.11
     replaced
    0.11
    Altern
    0.11
     substitutes
    0.10
     Replacement
    0.10
     Altern
    0.10
    Activations Density 0.000%

    No Known Activations