© 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. 89761
    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
    Ø·
    -0.09
    Ral
    -0.09
     Glad
    -0.09
    /is
    -0.09
     enforcing
    -0.09
     woes
    -0.08
     Means
    -0.08
    nis
    -0.08
    /en
    -0.08
     intended
    -0.08
    POSITIVE LOGITS
     inexperienced
    0.10
     unaware
    0.10
     wit
    0.09
     punct
    0.09
     newcom
    0.09
     ignor
    0.09
    cede
    0.09
     sept
    0.09
    ardu
    0.09
     Edward
    0.08
    Activations Density 0.000%

    No Known Activations