© 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. 16012
    Prev
    Next
    INDEX
    Explanations

    will find, would learn, might see

    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
     meticulously
    -0.10
     Marian
    -0.10
    _nl
    -0.09
    hari
    -0.09
     somehow
    -0.09
     exp
    -0.09
     Flores
    -0.09
     freak
    -0.09
     meticulous
    -0.09
     sloppy
    -0.09
    POSITIVE LOGITS
     benefit
    0.15
     appreciate
    0.15
     benefited
    0.15
     Benefit
    0.14
     Apprec
    0.14
     appreciation
    0.14
     grav
    0.13
     appreciated
    0.13
     apprec
    0.13
     benefiting
    0.12
    Activations Density 0.060%

    No Known Activations