© 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. 48865
    Prev
    Next
    INDEX
    Explanations

    another thing is

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ault
    -0.08
    pute
    -0.08
    PUTE
    -0.07
    ined
    -0.07
    086
    -0.07
    chio
    -0.07
     converse
    -0.07
    imbus
    -0.07
     dub
    -0.07
     hypo
    -0.07
    POSITIVE LOGITS
     important
    0.18
     thing
    0.18
     aspect
    0.18
     interesting
    0.18
     noteworthy
    0.17
     reason
    0.17
     contributing
    0.16
     notable
    0.15
     factor
    0.15
    important
    0.14
    Activations Density 0.061%

    No Known Activations