© 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. 111939
    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
    .edu
    -0.09
     Coke
    -0.09
    anan
    -0.09
    edu
    -0.09
     organic
    -0.08
    atto
    -0.08
    rant
    -0.08
     Bolt
    -0.08
    asco
    -0.08
    observation
    -0.08
    POSITIVE LOGITS
     behalf
    0.11
     Aval
    0.11
     aval
    0.11
     subtitle
    0.10
     rop
    0.10
    <|endoftext|>
    0.10
     provocative
    0.10
     inst
    0.10
    ilen
    0.10
     Brun
    0.10
    Activations Density 0.000%

    No Known Activations